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

    Neuronpedia

    INDEX
    Explanations

    possessive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *N
    -0.06
    -anchor
    -0.06
    upt
    -0.06
    _accessible
    -0.06
     jaar
    -0.06
     Gul
    -0.06
     phóng
    -0.06
     uri
    -0.06
     Week
    -0.06
    	ret
    -0.06
    POSITIVE LOGITS
     акт
    0.07
    _Char
    0.07
    etrize
    0.07
     ś
    0.06
     nuestras
    0.06
     اک
    0.06
     asker
    0.06
    .scss
    0.06
     πα
    0.06
     furry
    0.06
    Act Density 0.021%

    No Known Activations