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

    Neuronpedia

    INDEX
    Explanations

    This or basic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deton
    0.44
     bardzo
    0.43
     Ры
    0.43
     Также
    0.42
     danced
    0.42
     Bah
    0.41
     dignitaries
    0.41
     Villan
    0.41
     pada
    0.40
     dance
    0.40
    POSITIVE LOGITS
     fhall
    0.50
    óf
    0.48
    बी
    0.46
    苃
    0.45
    steelblue
    0.43
    ويض
    0.43
     irritated
    0.43
    νες
    0.42
    هيل
    0.42
    eses
    0.42
    Act Density 0.001%

    No Known Activations