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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Calder
    -0.07
     chast
    -0.07
     Trou
    -0.06
     Loren
    -0.06
    ”↵
    -0.06
    factor
    -0.06
     filtr
    -0.06
     Jac
    -0.06
     розк
    -0.06
     sounded
    -0.06
    POSITIVE LOGITS
    шего
    0.06
     Anh
    0.06
    หม
    0.06
    (Runtime
    0.06
    .untracked
    0.06
     الهند
    0.06
     анг
    0.06
    Keys
    0.06
     meziná
    0.05
     natur
    0.05
    Act Density 0.011%

    No Known Activations