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

    Neuronpedia

    INDEX
    Explanations

    ARD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    俊
    -0.07
     repmat
    -0.07
     delt
    -0.06
     happiest
    -0.06
    _negative
    -0.06
    (bytes
    -0.06
     rape
    -0.06
    φέ
    -0.06
    ]+
    -0.06
    .di
    -0.06
    POSITIVE LOGITS
    choose
    0.07
    Toggle
    0.07
     Opens
    0.07
    Jac
    0.07
    Dados
    0.07
     teng
    0.06
     suspicion
    0.06
    chure
    0.06
    -scenes
    0.06
     omission
    0.06
    Act Density 0.016%

    No Known Activations