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

    Neuronpedia

    INDEX
    Explanations

    rest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rich
    -0.07
    ”的
    -0.06
    bild
    -0.06
     عص
    -0.06
     Luc
    -0.06
    риг
    -0.06
     Todd
    -0.06
     Frank
    -0.06
     دیده
    -0.06
     Twelve
    -0.06
    POSITIVE LOGITS
     ′
    0.08
    ##
    0.07
    jal
    0.07
     deviceId
    0.07
    .dataset
    0.07
    .Now
    0.07
    ้เป
    0.07
    *a
    0.06
    _ids
    0.06
     respawn
    0.06
    Act Density 0.007%

    No Known Activations