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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _function
    -0.07
     fury
    -0.07
     logistics
    -0.07
    these
    -0.07
     Douglas
    -0.07
     sağlam
    -0.06
     ancient
    -0.06
    違い
    -0.06
    linux
    -0.06
     значение
    -0.06
    POSITIVE LOGITS
    จำนวน
    0.07
     ciała
    0.07
    CLUDING
    0.06
    HE
    0.06
    呐
    0.06
    @RestController
    0.06
    对方
    0.06
     الدم
    0.06
    PI
    0.06
     Pixels
    0.06
    Act Density 0.003%

    No Known Activations