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

    Neuronpedia

    INDEX
    Explanations

    time and date formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ادم
    -0.07
    EMPTY
    -0.07
    UNITY
    -0.07
    032
    -0.06
    ishment
    -0.06
    	flash
    -0.06
    (trim
    -0.06
    _IList
    -0.06
     โรง
    -0.06
    Ó
    -0.06
    POSITIVE LOGITS
    jie
    0.07
     entra
    0.06
    那些
    0.06
    past
    0.06
     침
    0.06
    .present
    0.06
     entrar
    0.06
     D
    0.06
    にと
    0.06
    isodes
    0.06
    Act Density 0.019%

    No Known Activations