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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ido
    -0.08
    适
    -0.07
    _feed
    -0.07
    analytics
    -0.07
     pronto
    -0.07
    indh
    -0.07
    Authorize
    -0.07
     favored
    -0.06
     Giov
    -0.06
     surve
    -0.06
    POSITIVE LOGITS
    leine
    0.07
    いて
    0.06
     fair
    0.06
    、な
    0.06
     �
    0.06
    Bron
    0.06
    NOW
    0.06
    族自治
    0.06
    AIL
    0.06
     NST
    0.06
    Act Density 0.037%

    No Known Activations