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

    Neuronpedia

    INDEX
    Explanations

    Unstructured text/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     могут
    -0.08
     может
    -0.07
     cabin
    -0.07
     cautious
    -0.06
    standing
    -0.06
     یعنی
    -0.06
    �
    -0.06
     Fortnite
    -0.06
     单
    -0.06
     чи
    -0.06
    POSITIVE LOGITS
    erce
    0.07
     Dare
    0.07
     deportation
    0.06
    Fold
    0.06
    .setEditable
    0.06
    胸
    0.06
    rice
    0.06
     belonged
    0.06
    SharedPreferences
    0.06
     adjust
    0.06
    Act Density 0.000%

    No Known Activations