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

    Neuronpedia

    INDEX
    Explanations

    ON

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᵴ
    -0.08
    ڝ
    -0.07
    蟆
    -0.07
     cunt
    -0.07
    createForm
    -0.07
    뷜
    -0.07
    網友
    -0.07
    .movie
    -0.07
    MY
    -0.07
    茑
    -0.06
    POSITIVE LOGITS
    东
    0.08
    ائم
    0.07
    _genes
    0.07
    קרי
    0.07
    权
    0.07
    	right
    0.07
    GP
    0.07
    -ROM
    0.07
    _Base
    0.07
    ieron
    0.07
    Act Density 0.001%

    No Known Activations