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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrays
    -0.07
     geography
    -0.07
    ?=
    -0.07
     *↵↵↵
    -0.07
     uphold
    -0.07
     Casino
    -0.07
    raquo
    -0.06
     processData
    -0.06
    ',...↵
    -0.06
     permutations
    -0.06
    POSITIVE LOGITS
    Phot
    0.06
    /mac
    0.06
    μιλος
    0.06
    _CREATED
    0.06
     sonrası
    0.06
    .FirebaseAuth
    0.06
    /extensions
    0.06
    Json
    0.06
    直接
    0.05
    رير
    0.05
    Act Density 0.039%

    No Known Activations