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

    Neuronpedia

    INDEX
    Explanations

    Wig

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	un
    -0.07
     -------------------------------------------------------------------------↵
    -0.06
    -0.06
     laundry
    -0.06
             
↵
    -0.06
     منذ
    -0.06
    -0.06
     Seit
    -0.06
     HPV
    -0.06
     waitFor
    -0.06
    POSITIVE LOGITS
    -gallery
    0.07
    constructed
    0.07
     грав
    0.07
    кул
    0.07
    リカ
    0.07
    itra
    0.07
    论坛
    0.06
    .Age
    0.06
    graduate
    0.06
    ifference
    0.06
    Act Density 0.007%

    No Known Activations