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

    Neuronpedia

    INDEX
    Explanations

    single

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .faceVertexUvs
    -0.07
     hatten
    -0.06
    	margin
    -0.06
     magical
    -0.06
    _callbacks
    -0.06
     PSD
    -0.06
     لن
    -0.06
     hn
    -0.06
     hatte
    -0.06
    Moves
    -0.06
    POSITIVE LOGITS
    aty
    0.07
    ленные
    0.07
    collect
    0.07
    _Begin
    0.06
     NSInteger
    0.06
     강
    0.06
    obar
    0.06
    519
    0.06
    Come
    0.06
     Ga
    0.06
    Act Density 0.018%

    No Known Activations