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
     perpetrator
    -0.07
     contributors
    -0.07
    .Comm
    -0.06
     unser
    -0.06
     _____
    -0.06
    -java
    -0.06
     distancing
    -0.06
     AOL
    -0.06
     Gür
    -0.06
     disappeared
    -0.06
    POSITIVE LOGITS
    Expansion
    0.07
    /li
    0.07
     SENSOR
    0.06
    bsd
    0.06
    γά
    0.06
     sở
    0.06
    惊
    0.06
     Sy
    0.06
    yp
    0.06
     suc
    0.06
    Act Density 0.054%

    No Known Activations