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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     numb
    -0.07
     tai
    -0.06
    ाहर
    -0.06
    имости
    -0.06
    []{
    -0.06
     siege
    -0.06
    OutOfBoundsException
    -0.06
    IU
    -0.06
    质
    -0.06
    脑
    -0.06
    POSITIVE LOGITS
    분석
    0.07
    �다
    0.07
    /interfaces
    0.06
    emm
    0.06
     ])↵↵
    0.06
    ])↵↵
    0.06
     appreciation
    0.06
     #-}↵
    0.06
    (())↵
    0.06
    られた
    0.06
    Act Density 0.047%

    No Known Activations