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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating references or citations

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

    Immediately before "Here's" or "Here is"

    np_acts-logits-general · gemini-2.0-flash

    Here's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.95
     '\\;'
    -0.85
    الدراسه
    -0.85
    expandindo
    -0.84
     صوتيه
    -0.84
     nahilalakip
    -0.80
    principalColumn
    -0.78
     autorytatywna
    -0.78
    تقاوى
    -0.77
    makeConstraints
    -0.77
    POSITIVE LOGITS
     some
    0.98
     how
    0.96
     what
    0.92
     a
    0.87
     another
    0.86
     my
    0.80
     the
    0.79
     our
    0.72
     an
    0.71
     why
    0.70
    Act Density 0.112%

    No Known Activations