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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cé
    -0.08
     saf
    -0.07
    ($('
    -0.07
    ཆ
    -0.07
     cruc
    -0.06
    /slider
    -0.06
     convertible
    -0.06
     وكل
    -0.06
    的第一
    -0.06
    牵手
    -0.06
    POSITIVE LOGITS
    )(
    0.07
    izzato
    0.07
    ORMAT
    0.07
    BOARD
    0.07
    颐
    0.07
    crypto
    0.06
    istas
    0.06
     psych
    0.06
    textContent
    0.06
    uma
    0.06
    Act Density 0.001%

    No Known Activations