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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fs
    -0.07
    Front
    -0.06
     unten
    -0.06
     Auf
    -0.06
    Ohio
    -0.06
     mediation
    -0.06
    levator
    -0.06
    acción
    -0.06
     activism
    -0.06
    sequelize
    -0.06
    POSITIVE LOGITS
     imread
    0.08
    goal
    0.06
     gösteren
    0.06
     canc
    0.06
     #$
    0.06
     []
↵
    0.06
     Möglichkeit
    0.06
    (draw
    0.06
     nå
    0.06
    版
    0.06
    Act Density 0.010%

    No Known Activations