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

    Neuronpedia

    INDEX
    Explanations

    Dam

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    」を
    -0.07
     вку
    -0.07
     velvet
    -0.07
    开始
    -0.07
    Creative
    -0.07
    식을
    -0.07
    uncio
    -0.06
    协
    -0.06
     certifications
    -0.06
     opciones
    -0.06
    POSITIVE LOGITS
     Dam
    0.16
     dam
    0.14
    Dam
    0.13
     dams
    0.11
    dam
    0.09
     DAM
    0.08
    am
    0.08
     Tam
    0.08
     tam
    0.08
    Tam
    0.07
    Act Density 0.007%

    No Known Activations