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

    Neuronpedia

    INDEX
    Explanations

    pattern

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    760
    -0.07
     Nude
    -0.07
    losure
    -0.07
    .Project
    -0.07
     золот
    -0.06
    _X
    -0.06
    ťan
    -0.06
     xp
    -0.06
    _GB
    -0.06
     SE
    -0.06
    POSITIVE LOGITS
     समझ
    0.07
     كبيرة
    0.06
    τικ
    0.06
     बय
    0.06
     انتخاب
    0.06
     شرق
    0.06
    Music
    0.06
     Brennan
    0.06
     contaminated
    0.06
    ılacak
    0.06
    Act Density 0.000%

    No Known Activations