Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that express appreciation and encouragement towards the reader

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following "you" (pronoun)

    np_acts-logits-general · gemini-2.0-flash

    finding or visiting places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Particularly
    -0.39
     Ster
    -0.35
     protoimpl
    -0.33
     Especially
    -0.31
     claro
    -0.31
     substantial
    -0.30
     particularly
    -0.30
     Absch
    -0.30
    }{*}{}
    -0.29
     prompt
    -0.28
    POSITIVE LOGITS
    AutoScaleMode
    0.74
     للمعارف
    0.65
     виправивши
    0.64
     utafitiHapana
    0.63
    rungsseite
    0.59
    ⓧ
    0.59
     iconLine
    0.57
     NSCoder
    0.57
     незавершена
    0.54
    tvguidetime
    0.53
    Act Density 0.190%

    No Known Activations