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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лися
    -0.07
     Independent
    -0.06
    son
    -0.06
    Children
    -0.06
    *$
    -0.06
    aker
    -0.06
    core
    -0.06
     Loren
    -0.06
    AKER
    -0.06
     Kl
    -0.06
    POSITIVE LOGITS
    武
    0.06
    Aus
    0.06
    .undefined
    0.06
    ucs
    0.06
    Nuitka
    0.06
    IService
    0.06
    ueva
    0.06
     raz
    0.06
    少
    0.06
    _DENIED
    0.06
    Act Density 0.003%

    No Known Activations