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

    Neuronpedia

    INDEX
    Explanations

    the beginning of documents or sections within documents

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

    Code or notation fragments

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal or technical code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RefNanny
    -0.46
     North
    -0.45
    Dear
    -0.44
    ab
    -0.43
     Dear
    -0.39
    ental
    -0.39
    hope
    -0.39
     N
    -0.38
    神
    -0.38
    ][
    -0.37
    POSITIVE LOGITS
     nahilalakip
    0.91
    })*/
    0.87
    ⓧ
    0.86
     unknownFields
    0.85
     Италијани
    0.84
     vPvB
    0.84
     ModelExpression
    0.81
     EconPapers
    0.80
    الإنجليزية
    0.73
    Tikang
    0.72
    Act Density 0.060%

    No Known Activations