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

    Neuronpedia

    INDEX
    Explanations

    Difference of squares

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     routes
    -0.09
     Kodi
    -0.08
     kaa
    -0.07
     carpets
    -0.07
    Determ
    -0.07
     determine
    -0.07
    agini
    -0.07
    cel
    -0.07
    Rf
    -0.07
    ordan
    -0.07
    POSITIVE LOGITS
     incremento
    0.09
    .mixin
    0.09
     Increment
    0.08
     september
    0.08
    ーク
    0.08
    .increment
    0.08
     Einzahlung
    0.08
     bħala
    0.08
    -fashioned
    0.08
     preb
    0.08
    Act Density 0.025%

    No Known Activations