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

    Neuronpedia

    INDEX
    Explanations

    code files

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruk
    -0.08
     commentator
    -0.07
    zek
    -0.07
    PRS
    -0.06
    ids
    -0.06
    .cos
    -0.06
     aus
    -0.06
     urn
    -0.06
     turns
    -0.06
    _WARN
    -0.06
    POSITIVE LOGITS
     flute
    0.07
     Avengers
    0.07
    -common
    0.06
     Initialise
    0.06
    ;?>↵
    0.06
    igration
    0.06
    (val
    0.06
     ''){↵
    0.06
    UPDATED
    0.06
    �
    0.06
    Act Density 0.003%

    No Known Activations