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

    Neuronpedia

    INDEX
    Explanations

    46 or 47

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     three
    -0.07
    ren
    -0.07
     dissertation
    -0.07
     Three
    -0.07
    _directory
    -0.06
     flown
    -0.06
     sw
    -0.06
    FC
    -0.06
     CF
    -0.06
    Unit
    -0.06
    POSITIVE LOGITS
     pageInfo
    0.07
    เผ
    0.07
    ��
    0.06
    yyvsp
    0.06
     씨
    0.06
    ิพ
    0.06
    \Has
    0.06
     pisc
    0.06
     cenu
    0.06
     ヴ
    0.06
    Act Density 0.010%

    No Known Activations