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

    Neuronpedia

    INDEX
    Explanations

    references to file paths and identifiers in coding or technical contexts

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

    paths and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.66
    UnusedPrivate
    -0.58
    AsUp
    -0.56
    Personendaten
    -0.54
    LookAnd
    -0.53
     betweenstory
    -0.52
     Photocase
    -0.51
    stylers
    -0.49
    Tikang
    -0.47
    ➯
    -0.47
    POSITIVE LOGITS
    __(/*!
    0.77
     './
    0.73
     "./
    0.64
     ['./
    0.59
    ('./
    0.59
     '../
    0.59
     '
    0.56
    各样的
    0.55
    ../../
    0.53
    ="../
    0.51
    Act Density 0.000%

    No Known Activations