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

    Neuronpedia

    INDEX
    Explanations

    boolean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    大臣
    -0.07
    ינ
    -0.07
    .component
    -0.07
    [url
    -0.07
    亮度
    -0.07
    monitor
    -0.07
    _cfg
    -0.07
    爟
    -0.07
    但由于
    -0.07
    iti
    -0.07
    POSITIVE LOGITS
    .Track
    0.08
    אהבה
    0.07
    LOPT
    0.07
    🖏
    0.07
    stores
    0.06
     nou
    0.06
    ﳋ
    0.06
    SelectionMode
    0.06
    _Selected
    0.06
    🎟
    0.06
    Act Density 0.048%

    No Known Activations