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

    Neuronpedia

    INDEX
    Explanations

    recalls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Negot
    -0.07
    опас
    -0.07
     presentation
    -0.07
    tn
    -0.06
     condom
    -0.06
    _RGBA
    -0.06
    KD
    -0.06
    ूड
    -0.06
     conc
    -0.06
     Freder
    -0.06
    POSITIVE LOGITS
    ['_
    0.07
     >&
    0.07
    有的
    0.06
     EFI
    0.06
    ＼＼
    0.06
    Aligned
    0.06
    /android
    0.06
    	throws
    0.06
    _pick
    0.06
     ikke
    0.06
    Act Density 0.006%

    No Known Activations