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
     стоит
    -0.07
    /ex
    -0.07
    increase
    -0.06
     centroid
    -0.06
     nghe
    -0.06
     zjist
    -0.06
    ponge
    -0.06
     showers
    -0.06
    incinnati
    -0.06
    っても
    -0.06
    POSITIVE LOGITS
     �
    0.07
    像
    0.07
     Encode
    0.07
     TOO
    0.07
    .Padding
    0.06
    Esta
    0.06
    _LESS
    0.06
    Este
    0.06
    類
    0.06
     commands
    0.06
    Act Density 0.000%

    No Known Activations