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

    Neuronpedia

    INDEX
    Explanations

    the importance of preventive measures in health or safety contexts

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

    Follows punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    punctuation and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SharedDtor
    -0.91
    :✨
    -0.84
     otomatig
    -0.83
     Efq
    -0.81
     ―――――
    -0.80
     tvb
    -0.77
     transfieras
    -0.75
     ModelExpression
    -0.75
    ppure
    -0.74
     autorytatywna
    -0.72
    POSITIVE LOGITS
     that
    0.74
     because
    0.69
     I
    0.66
     basically
    0.64
     not
    0.61
     so
    0.61
     [
    0.60
     et
    0.59
     So
    0.59
     
    0.56
    Act Density 0.089%

    No Known Activations