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

    Neuronpedia

    INDEX
    Explanations

    framework, conversations, investigation, contracts, nest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LA
    0.47
    LE
    0.46
    SAN
    0.46
    CAS
    0.45
    BIN
    0.44
    eni
    0.42
    AT
    0.42
    UT
    0.41
    KIT
    0.41
    SE
    0.41
    POSITIVE LOGITS
     eğ
    0.49
     قیام
    0.49
     시민
    0.47
    페이지
    0.47
    aży
    0.46
     înd
    0.46
     기간
    0.45
     सिंघ
    0.45
     далі
    0.45
     एग्जाम
    0.44
    Act Density 0.000%

    No Known Activations