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

    Neuronpedia

    INDEX
    Explanations

    giving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ATEST
    -0.08
     bit
    -0.07
    ust
    -0.07
    老旧
    -0.07
     short
    -0.07
     yük
    -0.07
    ニュ
    -0.07
    _vector
    -0.07
     USB
    -0.07
    长沙
    -0.07
    POSITIVE LOGITS
     możli
    0.07
    Phase
    0.06
    真實
    0.06
    حة
    0.06
     resale
    0.06
    ijken
    0.06
     They
    0.06
    .info
    0.06
    iciones
    0.06
    כתיבה
    0.06
    Act Density 0.022%

    No Known Activations