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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bil
    -0.07
    .leading
    -0.07
     anmeld
    -0.06
    Classification
    -0.06
    _HELPER
    -0.06
     STOP
    -0.06
    _Email
    -0.06
     porno
    -0.06
    -0.06
     Variation
    -0.06
    POSITIVE LOGITS
     insightful
    0.07
    	socket
    0.07
    镇
    0.07
    щё
    0.07
    派
    0.06
    mal
    0.06
     Sunshine
    0.06
    ardi
    0.06
    щими
    0.06
     previously
    0.06
    Act Density 0.001%

    No Known Activations