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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ild
    -0.07
    etration
    -0.07
    روم
    -0.07
     đất
    -0.06
     Ipsum
    -0.06
    yy
    -0.06
     penetration
    -0.06
    .range
    -0.06
    (artist
    -0.06
     flashlight
    -0.06
    POSITIVE LOGITS
     Newsletter
    0.07
    *this
    0.06
    Secondary
    0.06
     je
    0.06
     ป
    0.06
    Bio
    0.06
    COMM
    0.06
    ]*
    0.06
     ECS
    0.06
    ukt
    0.06
    Act Density 0.001%

    No Known Activations