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

    Neuronpedia

    INDEX
    Explanations

    sentences indicating certainty or affirmations

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

    "This is" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    is followed by reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ChildScrollView
    -0.83
    IContainer
    -0.81
     referenties
    -0.79
    itemBuilder
    -0.76
    getSeconds
    -0.75
     autorytatywna
    -0.73
     gynhyrchwyd
    -0.72
    principalColumn
    -0.72
     Baillargeon
    -0.72
    WithIOException
    -0.72
    POSITIVE LOGITS
     because
    1.04
     why
    0.88
    because
    0.81
     especially
    0.80
     porque
    0.79
     despite
    0.77
     Because
    0.76
    Because
    0.75
     fordi
    0.69
     particularly
    0.67
    Act Density 0.355%

    No Known Activations