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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pizza
    -0.07
     Instances
    -0.07
    Founded
    -0.06
    pecial
    -0.06
     rupt
    -0.06
     Urban
    -0.06
    _em
    -0.06
    CID
    -0.06
    vap
    -0.06
    мир
    -0.06
    POSITIVE LOGITS
    体育
    0.07
     В
    0.06
     cgi
    0.06
     accelerometer
    0.06
    )",
    0.06
     meng
    0.06
     Clamp
    0.06
    @mail
    0.06
    _oauth
    0.06
    "}}
    0.06
    Act Density 0.168%

    No Known Activations