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

    Neuronpedia

    INDEX
    Explanations

    SET

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     variance
    -0.06
    column
    -0.06
    iance
    -0.06
    .POS
    -0.06
     defiant
    -0.06
    795
    -0.06
     procession
    -0.06
     vě
    -0.06
    ula
    -0.06
     redes
    -0.06
    POSITIVE LOGITS
    代
    0.08
    Estimated
    0.07
     Estimated
    0.07
    \DB
    0.07
    	Created
    0.07
    -gen
    0.07
     Tag
    0.07
    .fromCharCode
    0.07
    .js
    0.06
    町
    0.06
    Act Density 0.004%

    No Known Activations