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

    Neuronpedia

    INDEX
    Explanations

    disagreement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     besten
    -0.07
    ете
    -0.07
    Overlap
    -0.07
    Fu
    -0.06
    odka
    -0.06
    Protection
    -0.06
     ally
    -0.06
    ет
    -0.06
    academic
    -0.06
    RW
    -0.06
    POSITIVE LOGITS
     JsonSerializer
    0.06
    (col
    0.06
    (pc
    0.06
    ृष
    0.06
    ilmington
    0.06
     fq
    0.06
    xbd
    0.06
     honesty
    0.06
     математи
    0.06
    дром
    0.06
    Act Density 0.105%

    No Known Activations