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

    Neuronpedia

    INDEX
    Explanations

    word completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    efon
    -0.09
    ;br
    -0.09
    éĴ®
    -0.09
    yonel
    -0.09
    angered
    -0.08
    xae
    -0.08
    plier
    -0.08
    plx
    -0.08
    ypad
    -0.08
     Burl
    -0.08
    POSITIVE LOGITS
    ï½
    0.11
    ï¿
    0.09
    
    0.09
     aff
    0.09
    rt
    0.09
    ation
    0.08
    _cpp
    0.08
     Emb
    0.08
    ournal
    0.08
    ories
    0.08
    Act Density 0.292%

    No Known Activations