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

    Neuronpedia

    INDEX
    Explanations

    policy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tmp
    -0.07
     FUNCT
    -0.07
     trường
    -0.06
     staffer
    -0.06
    .mkdirs
    -0.06
    .X
    -0.06
     ************************
    -0.06
     الأف
    -0.06
    lı
    -0.06
     чес
    -0.06
    POSITIVE LOGITS
     showing
    0.07
     �
    0.07
     должны
    0.07
    iring
    0.06
    सम
    0.06
    abus
    0.06
     bağ
    0.06
    _met
    0.06
    SPAN
    0.06
    채
    0.06
    Act Density 0.005%

    No Known Activations