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

    Neuronpedia

    INDEX
    Explanations

    .create

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ingredients
    -0.07
    入れ
    -0.07
    晋江
    -0.07
    .Username
    -0.07
    (Paint
    -0.06
    ney
    -0.06
    檐
    -0.06
    ၊
    -0.06
    |string
    -0.06
    חשב
    -0.06
    POSITIVE LOGITS
    _PC
    0.07
     hoop
    0.07
    _act
    0.07
    ificent
    0.07
     app
    0.06
     harming
    0.06
     continual
    0.06
     Gone
    0.06
     waving
    0.06
     PendingIntent
    0.06
    Act Density 0.008%

    No Known Activations