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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sitcom
    -0.07
    群
    -0.07
    У
    -0.07
    انی
    -0.07
    Davis
    -0.07
    دهم
    -0.06
     priv
    -0.06
     LLP
    -0.06
     trades
    -0.06
    论文
    -0.06
    POSITIVE LOGITS
     Ton
    0.07
    bur
    0.07
    mitters
    0.06
     PWM
    0.06
    วล
    0.06
     animateWithDuration
    0.06
    _cos
    0.06
    .Mutex
    0.06
     Caps
    0.06
    appy
    0.06
    Act Density 0.044%

    No Known Activations