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

    Neuronpedia

    INDEX
    Explanations

    That

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leo
    -0.06
     books
    -0.06
    pend
    -0.06
     rm
    -0.06
    'H
    -0.06
    足
    -0.06
     multiplier
    -0.06
     totiž
    -0.06
     step
    -0.06
     chấm
    -0.06
    POSITIVE LOGITS
    -gnu
    0.06
    挥
    0.06
    aná
    0.06
     الاس
    0.06
     Sri
    0.06
    Globals
    0.06
    ibold
    0.06
    σμα
    0.06
    sidebar
    0.06
    Sibling
    0.06
    Act Density 0.000%

    No Known Activations