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

    Neuronpedia

    INDEX
    Explanations

    statements or questions regarding truth and beliefs, often associated with symbolic implications

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

    after commas

    np_acts-logits-general · gemini-2.0-flash

    imagine, think, look, remember

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    τως
    -0.55
    TestingModule
    -0.54
    TypedDataSet
    -0.51
    どうやら
    -0.51
    发表于
    -0.51
    thâu
    -0.49
     tačiau
    -0.49
    scriptcase
    -0.48
     tanto
    -0.48
     propOrder
    -0.48
    POSITIVE LOGITS
     imagine
    1.79
     look
    1.72
     remember
    1.61
     think
    1.58
    look
    1.55
    imagine
    1.54
     Imagine
    1.53
     Look
    1.53
    Look
    1.52
    Imagine
    1.51
    Act Density 0.427%

    No Known Activations