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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and encouragement towards the user

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

    you or user asks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flü
    -0.34
     WARD
    -0.32
    Bromoform
    -0.31
     claro
    -0.31
    -0.31
    +:+
    -0.29
     cantit
    -0.29
     Ward
    -0.29
     Ster
    -0.29
     विभ
    -0.29
    POSITIVE LOGITS
     nakalista
    0.76
     незавершена
    0.65
    AutoScaleMode
    0.63
    tvguidetime
    0.62
     queſta
    0.60
     iconLine
    0.60
     utafitiHapana
    0.59
    rungsseite
    0.59
     للمعارف
    0.56
    ⓧ
    0.55
    Act Density 0.051%

    No Known Activations