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

    Neuronpedia

    INDEX
    Explanations

    6

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carry
    0.67
     à
    0.66
     carrying
    0.64
     atau
    0.63
     or
    0.61
     ter
    0.60
     लेंगे
    0.60
     semi
    0.58
     frag
    0.57
     bon
    0.57
    POSITIVE LOGITS
    ൧
    0.77
    itiis
    0.77
     Jwt
    0.73
     краски
    0.73
    adiator
    0.72
    REETYPE
    0.69
    ITO
    0.69
     gelişmeler
    0.69
    రికి
    0.67
     negroes
    0.67
    Act Density 0.217%

    No Known Activations