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

    Neuronpedia

    INDEX
    Explanations

    state or defining phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    WCHAR
    0.45
    ెల
    0.40
     Activated
    0.40
     প্রশাস
    0.39
     Serviço
    0.39
    localVarPath
    0.38
     وضاحت
    0.38
    သွ
    0.37
    요일
    0.37
    masına
    0.37
    POSITIVE LOGITS
     testimonial
    0.41
     back
    0.40
     profe
    0.40
    ass
    0.39
    សម
    0.39
     nah
    0.38
    ayet
    0.38
     stranded
    0.38
     конфи
    0.38
    endo
    0.38
    Act Density 0.001%

    No Known Activations