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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sala
    -0.07
    */,
    -0.07
    ksiyon
    -0.06
     machen
    -0.06
     Mezi
    -0.06
     propia
    -0.06
    imators
    -0.06
    ako
    -0.06
     zbo
    -0.06
     zoek
    -0.06
    POSITIVE LOGITS
     remot
    0.07
     Mozilla
    0.07
     temper
    0.07
     tournament
    0.07
     Native
    0.07
    522
    0.06
     mutating
    0.06
    gom
    0.06
     FLAC
    0.06
     Entity
    0.06
    Act Density 0.004%

    No Known Activations