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

    Neuronpedia

    INDEX
    Explanations

    Code integrity hashes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    供大家
    -0.08
    nestjs
    -0.08
    อำนวยความ
    -0.07
    WRAPPER
    -0.07
     yaptığı
    -0.07
    Payments
    -0.07
    泸州
    -0.07
    修炼
    -0.07
    Received
    -0.07
    RuleContext
    -0.07
    POSITIVE LOGITS
    -o
    0.07
    增长
    0.07
    _arm
    0.07
     affirm
    0.07
     DISP
    0.07
    יבות
    0.06
    (cos
    0.06
    _crit
    0.06
    規定
    0.06
    اوي
    0.06
    Act Density 0.002%

    No Known Activations