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

    Neuronpedia

    INDEX
    Explanations

    internet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    处处长
    -0.08
     flank
    -0.07
     Missile
    -0.07
     كو
    -0.07
    CHandle
    -0.07
     Marshal
    -0.07
    ળ
    -0.07
     thoát
    -0.07
    官员
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    -\
    0.07
    _eg
    0.07
    Eine
    0.07
    Lines
    0.07
     ""↵
    0.07
    落幕
    0.07
    ъ
    0.07
    静电
    0.07
    伝え
    0.07
    ample
    0.07
    Act Density 0.014%

    No Known Activations