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

    Neuronpedia

    INDEX
    Explanations

    whoa! surprise exclamation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bas
    0.68
    most
    0.67
    DNA
    0.67
    你
    0.67
    Per
    0.67
    Senior
    0.66
     the
    0.66
    Sud
    0.66
     per
    0.65
     latent
    0.65
    POSITIVE LOGITS
    pped
    1.16
    ops
    1.12
    pping
    1.02
    ître
    0.98
     wouldn
    0.96
    opee
    0.95
     powiedział
    0.94
     knows
    0.93
     invented
    0.92
     dijeron
    0.91
    Act Density 0.010%

    No Known Activations