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

    Neuronpedia

    INDEX
    Explanations

    technical terms and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jednej
    0.69
     retten
    0.55
     často
    0.55
    往往
    0.54
    CFBundle
    0.54
    웜
    0.54
    amort
    0.53
    editar
    0.53
    os
    0.52
    often
    0.52
    POSITIVE LOGITS
    ividual
    0.66
    自身の
    0.63
    自分の
    0.58
     jiv
    0.57
    乃至
    0.56
     নিজের
    0.55
    自己的
    0.55
    自身的
    0.53
     creen
    0.53
     meaningful
    0.52
    Act Density 0.004%

    No Known Activations