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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Projection
    -0.06
    寸
    -0.06
    賢
    -0.06
     millennium
    -0.06
     metrics
    -0.06
     Decay
    -0.06
    ={!
    -0.06
     symmetry
    -0.06
    IJ
    -0.06
     Threshold
    -0.06
    POSITIVE LOGITS
     brass
    0.07
     platí
    0.06
    лий
    0.06
    ุลาคม
    0.06
    (Transaction
    0.06
    าถ
    0.06
     thật
    0.06
    _complete
    0.06
     mohl
    0.06
    alin
    0.06
    Act Density 0.009%

    No Known Activations