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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     अत
    -0.07
     próximo
    -0.07
    473
    -0.07
     Sat
    -0.07
     прип
    -0.06
     Lenovo
    -0.06
    81
    -0.06
    иг
    -0.06
     иг
    -0.06
     ас
    -0.06
    POSITIVE LOGITS
    oust
    0.07
     coronary
    0.07
    (nav
    0.07
    omedical
    0.07
     transforms
    0.06
     avoiding
    0.06
     {},
    0.06
    ुँ
    0.06
    osopher
    0.06
    -times
    0.06
    Act Density 0.056%

    No Known Activations