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

    Neuronpedia

    INDEX
    Explanations

    "//"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    acción
    -0.07
    ﺒ
    -0.07
    ��
    -0.07
    (wait
    -0.07
    אמין
    -0.07
     �
    -0.07
    itesse
    -0.07
    .qt
    -0.06
     mouseX
    -0.06
    ricing
    -0.06
    POSITIVE LOGITS
    줬
    0.07
     Blast
    0.07
     fo
    0.07
     barrel
    0.07
    favor
    0.07
    옜
    0.07
     ideal
    0.06
    千米
    0.06
     optics
    0.06
    /token
    0.06
    Act Density 0.001%

    No Known Activations