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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     liter
    -0.07
     NB
    -0.06
     :/
    -0.06
    antiago
    -0.06
     Comfort
    -0.06
     بهره
    -0.06
    tracks
    -0.06
    _CS
    -0.06
     CB
    -0.06
    /false
    -0.06
    POSITIVE LOGITS
    neighbors
    0.07
     GOODMAN
    0.07
    (win
    0.06
    zelf
    0.06
     Ảnh
    0.06
    esseract
    0.06
    _codes
    0.06
    DAC
    0.06
     apart
    0.06
    ас
    0.06
    Act Density 0.000%

    No Known Activations