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

    Neuronpedia

    INDEX
    Explanations

    long periods of engagement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Argentina
    -0.08
     nu
    -0.07
     Philadelphia
    -0.07
     інозем
    -0.07
     Portugal
    -0.07
    еся
    -0.07
     EditorGUILayout
    -0.07
     Joseph
    -0.06
    utr
    -0.06
    ammu
    -0.06
    POSITIVE LOGITS
    .black
    0.07
    OTOS
    0.07
     pca
    0.06
     Finn
    0.06
    .jms
    0.06
    .Chrome
    0.06
    Signing
    0.06
     categorie
    0.06
     lever
    0.05
    +-+-+-+-+-+-+-+-
    0.05
    Act Density 0.018%

    No Known Activations