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

    Neuronpedia

    INDEX
    Explanations

    structure and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    하여
    0.46
     gent
    0.44
    혁
    0.44
    \{
    0.44
     pup
    0.43
     στρα
    0.43
    สวน
    0.43
    EVA
    0.43
     stereotypes
    0.43
     précision
    0.43
    POSITIVE LOGITS
    ajt
    0.47
    स
    0.45
    نس
    0.45
    ক্তিক
    0.43
    си
    0.43
    ेंटीना
    0.42
    ana
    0.42
     Оде
    0.42
    equation
    0.41
    esi
    0.41
    Act Density 0.001%

    No Known Activations