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

    Neuronpedia

    INDEX
    Explanations

    Force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     是
    -0.08
    Executable
    -0.08
    heets
    -0.07
     Compound
    -0.07
     shared
    -0.07
    Frank
    -0.07
     physicist
    -0.07
    ニュ
    -0.07
    minent
    -0.07
    uliar
    -0.07
    POSITIVE LOGITS
     prohibits
    0.07
    lastName
    0.07
    _PS
    0.07
     tín
    0.07
    itez
    0.07
    kad
    0.07
    isEnabled
    0.06
    ㈬
    0.06
    EndDate
    0.06
    ཏ
    0.06
    Act Density 0.012%

    No Known Activations