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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mb
    -0.07
     predic
    -0.06
     нич
    -0.06
    ++;
    -0.06
     radicals
    -0.06
     pooling
    -0.06
    ZY
    -0.06
    ––
    -0.06
    .n
    -0.06
     отрим
    -0.06
    POSITIVE LOGITS
    avier
    0.08
    ожд
    0.07
     driveway
    0.07
     ран
    0.07
     estimator
    0.07
    연
    0.06
     تع
    0.06
     strangers
    0.06
     Puppy
    0.06
     Zusammen
    0.06
    Act Density 0.000%

    No Known Activations