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

    Neuronpedia

    INDEX
    Explanations

    Technical/code related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🌳
    -0.07
    ő
    -0.07
    סעיף
    -0.07
    _digit
    -0.07
    Ꮎ
    -0.07
    pNext
    -0.07
    Marco
    -0.07
     למ
    -0.07
    потен
    -0.07
    iox
    -0.06
    POSITIVE LOGITS
    (...
    0.08
    切换
    0.08
    -variable
    0.07
    	y
    0.07
    .bg
    0.07
    ذر
    0.07
    調
    0.07
     usually
    0.07
    ➘
    0.06
    -initial
    0.06
    Act Density 0.000%

    No Known Activations