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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing performance or quality

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

    fantastic job

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сылкі
    -0.59
    Rptr
    -0.53
     incrí
    -0.51
     newOwner
    -0.50
    ValueStyle
    -0.50
    transQ
    -0.49
    󠁢
    -0.48
     InputDecoration
    -0.48
    teos
    -0.48
    躇
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    0.35
     previous
    0.33
     gebo
    0.33
     respectivas
    0.32
     encuent
    0.31
     slaap
    0.31
    Jereo
    0.31
     prochaines
    0.31
     siguientes
    0.30
     dernières
    0.30
    Act Density 0.164%

    No Known Activations