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

    Neuronpedia

    INDEX
    Explanations

    prohibits harmful content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Large
    0.96
     Многие
    0.90
     Unlike
    0.90
     Tuck
    0.89
     Lim
    0.89
    ={\
    0.86
     Although
    0.85
     SVM
    0.84
     Pixel
    0.84
     Ин
    0.82
    POSITIVE LOGITS
    ऩे
    1.12
    forbidden
    1.07
    ै
    1.05
    stood
    0.99
    ’”
    0.95
    ́
    0.94
    NavigationBar
    0.93
     impass
    0.92
    ं
    0.92
     démar
    0.91
    Act Density 0.427%

    No Known Activations