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

    Neuronpedia

    INDEX
    Explanations

    markdown and code clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    0.55
    ا
    0.47
     satisf
    0.45
    asma
    0.45
    满意
    0.45
     Repl
    0.45
    యోగ
    0.45
    을
    0.45
    اك
    0.44
    elh
    0.44
    POSITIVE LOGITS
     vaguely
    0.44
     cephal
    0.44
    sponsored
    0.44
     upgrading
    0.43
     مواليد
    0.42
     tratado
    0.41
     barracks
    0.41
     corso
    0.41
     vutt
    0.40
     बेबी
    0.40
    Act Density 0.000%

    No Known Activations