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

    Neuronpedia

    INDEX
    Explanations

    _loader

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Communic
    -0.08
    BTN
    -0.08
    快讯
    -0.07
    _distance
    -0.07
     freshmen
    -0.07
     fills
    -0.07
    笑
    -0.07
    agini
    -0.07
     Restaurant
    -0.07
    _CAPACITY
    -0.07
    POSITIVE LOGITS
     included
    0.07
    rieg
    0.07
    เย
    0.07
    .take
    0.06
    UFACT
    0.06
    Making
    0.06
     прот
    0.06
    굽
    0.06
     sitcom
    0.06
     reproductive
    0.06
    Act Density 0.002%

    No Known Activations