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

    Neuronpedia

    INDEX
    Explanations

    1-800-FLOWERS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ığım
    0.44
    வின்
    0.44
    population
    0.42
    ों
    0.42
    कांच्या
    0.42
    ivating
    0.40
    ithin
    0.40
    iffent
    0.39
    বার
    0.38
    ným
    0.38
    POSITIVE LOGITS
     (
    0.70
    （
    0.59
     ;
    0.53
    ;
    0.52
    .;
    0.50
     （
    0.48
     試験
    0.44
     [
    0.43
    (_
    0.43
     ベ
    0.42
    Act Density 0.000%

    No Known Activations