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

    Neuronpedia

    INDEX
    Explanations

    emulate machine compliments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Op
    0.43
     Roll
    0.40
     Lois
    0.39
     scene
    0.39
     pitch
    0.37
     audiences
    0.37
     roll
    0.37
     Público
    0.36
     op
    0.35
     Lo
    0.35
    POSITIVE LOGITS
     خاصيه
    0.47
    exam
    0.40
    ",'
    0.39
    ющим
    0.37
     SIE
    0.37
     vreme
    0.36
    いを
    0.36
    userAgent
    0.36
    Fishing
    0.36
     സ്ഥാന
    0.36
    Act Density 0.001%

    No Known Activations