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

    Neuronpedia

    INDEX
    Explanations

    full

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forces
    -0.08
    _be
    -0.07
     open
    -0.07
     walls
    -0.07
    .hh
    -0.07
    .sal
    -0.07
     boxed
    -0.07
     enlisted
    -0.07
    FileVersion
    -0.07
    bean
    -0.07
    POSITIVE LOGITS
    (piece
    0.07
    _pct
    0.07
     Cardio
    0.06
     voyeur
    0.06
     InputDecoration
    0.06
    Kick
    0.06
     gastro
    0.06
     itemprop
    0.06
     Sprite
    0.06
     Bài
    0.06
    Act Density 0.007%

    No Known Activations