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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fashion
    -0.07
     Posted
    -0.07
     manner
    -0.07
     Scale
    -0.06
    iais
    -0.06
    Updated
    -0.06
    center
    -0.06
     Hed
    -0.06
    žití
    -0.06
    National
    -0.06
    POSITIVE LOGITS
    ,max
    0.06
    _PADDING
    0.06
    .TH
    0.06
     acknowledging
    0.06
     пояс
    0.06
     QTimer
    0.06
    ў
    0.06
    _down
    0.06
     tespit
    0.06
    ','"+
    0.06
    Act Density 0.016%

    No Known Activations