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

    Neuronpedia

    INDEX
    Explanations

    function parameter description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.82
     anciennes
    0.68
     attaque
    0.66
     antennes
    0.65
     chandelier
    0.61
    તે
    0.61
     stabbing
    0.61
     fortes
    0.60
     supérieures
    0.60
     esophageal
    0.60
    POSITIVE LOGITS
    on
    0.85
     в
    0.80
    п
    0.76
    in
    0.69
     in
    0.69
     is
    0.68
    file
    0.67
    ‬‬
    0.64
    在
    0.59
    氀
    0.59
    Act Density 0.010%

    No Known Activations