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

    Neuronpedia

    INDEX
    Explanations

    instances of forward slashes used in code or file paths

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

    file paths with packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stat
    -0.45
     %.
    -0.45
    XtraBars
    -0.43
    NOPQRST
    -0.42
    rinfo
    -0.42
     الحره
    -0.42
     HttpNotFound
    -0.41
    .=
    -0.41
    Tikang
    -0.40
    )_
    -0.39
    POSITIVE LOGITS
    __(/*!
    0.68
     nahilalakip
    0.61
    Parcelize
    0.57
     kasarigan
    0.55
    verifyException
    0.54
     AssemblyCompany
    0.51
     eşofman
    0.50
     kumaş
    0.47
     ibunya
    0.44
    Skocz
    0.43
    Act Density 0.000%

    No Known Activations