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

    Neuronpedia

    INDEX
    Explanations

    365

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zayıf
    -0.07
    ็นต
    -0.07
    732
    -0.06
     Supervisor
    -0.06
    ��
    -0.06
    "=>$
    -0.06
    撃
    -0.06
    ayıf
    -0.06
    jišť
    -0.06
    搞
    -0.06
    POSITIVE LOGITS
    365
    0.31
    356
    0.07
     staged
    0.07
    sprintf
    0.07
    仪
    0.07
     enhanced
    0.07
     جشن
    0.06
    Freedom
    0.06
    TypeInfo
    0.06
    [dir
    0.06
    Act Density 0.001%

    No Known Activations