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

    Neuronpedia

    INDEX
    Explanations

    Legal summaries and orders

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    깸
    -0.07
    _CAN
    -0.07
    ollision
    -0.07
     Let
    -0.07
    _VERTICAL
    -0.07
     reasons
    -0.07
     Verg
    -0.07
     האירוע
    -0.07
    切除
    -0.06
    绘制
    -0.06
    POSITIVE LOGITS
    菡
    0.08
    ��
    0.07
     killing
    0.07
    (stack
    0.07
    销售收入
    0.07
     Quotes
    0.06
    <S
    0.06
    号楼
    0.06
    ﲆ
    0.06
     {!!
    0.06
    Act Density 0.145%

    No Known Activations