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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rog
    0.71
    eer
    0.70
    na
    0.70
    ting
    0.66
    tres
    0.65
    я
    0.64
    ayn
    0.63
     devil
    0.62
    nap
    0.62
    market
    0.61
    POSITIVE LOGITS
    <unused2177>
    1.05
     ఇతర
    0.99
    neutrophiles
    0.95
    <unused569>
    0.90
    <unused2187>
    0.89
    借助
    0.89
     каких
    0.89
    ementara
    0.88
    <unused1702>
    0.88
    FLICT
    0.88
    Act Density 0.080%

    No Known Activations