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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "think" and its variations, indicating contemplation or reflection

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

    And here is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    horabuena
    -0.44
     humanidade
    -0.41
    industria
    -0.38
    تقاوى
    -0.38
     presença
    -0.38
     Alva
    -0.36
     Branche
    -0.36
     PROCEED
    -0.36
    rungsseite
    -0.36
    Autoritní
    -0.35
    POSITIVE LOGITS
     textStatus
    0.47
    $_['
    0.46
    StructEnd
    0.45
    msgTypes
    0.45
    Cursors
    0.45
    RTLR
    0.44
     لينك
    0.44
    IContainer
    0.43
    Boas
    0.42
    ClientRect
    0.42
    Act Density 0.083%

    No Known Activations