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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Marvel
    -0.07
    ्ल
    -0.07
    (min
    -0.06
     painful
    -0.06
    services
    -0.06
    ур
    -0.06
    ھ
    -0.06
    Lic
    -0.06
    оглас
    -0.06
    ,model
    -0.06
    POSITIVE LOGITS
    .abort
    0.07
    	tag
    0.06
    _COMPLETE
    0.06
     handleMessage
    0.06
    /el
    0.06
     Cardio
    0.06
    abis
    0.06
     Karel
    0.06
    355
    0.06
    removeClass
    0.06
    Act Density 0.002%

    No Known Activations