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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     opposed
    -0.06
    บาท
    -0.06
     oceans
    -0.06
     mixer
    -0.06
     lapse
    -0.06
     untouched
    -0.06
    .vars
    -0.06
     Edgar
    -0.06
    -eight
    -0.05
     scalar
    -0.05
    POSITIVE LOGITS
     Kamp
    0.07
    搜
    0.06
    форма
    0.06
     다운로드
    0.06
    _search
    0.06
    结合
    0.06
    bash
    0.06
    =df
    0.06
    丘
    0.06
    =P
    0.06
    Act Density 0.144%

    No Known Activations