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

    Neuronpedia

    INDEX
    Explanations

    rules or configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    학교
    -0.07
    -slider
    -0.07
    ்�
    -0.06
     Providence
    -0.06
    -flight
    -0.06
     Stop
    -0.06
    .activity
    -0.06
     зас
    -0.06
    itemap
    -0.06
     ADS
    -0.06
    POSITIVE LOGITS
    bservable
    0.07
     Worse
    0.07
     dull
    0.06
    orable
    0.06
     concatenated
    0.06
     Cyan
    0.06
    Luc
    0.06
    иму
    0.06
    Slash
    0.06
     sets
    0.06
    Act Density 0.002%

    No Known Activations