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

    Neuronpedia

    INDEX
    Explanations

    variations, size, differences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     obrig
    -0.07
    /cli
    -0.07
     �
    -0.07
     rych
    -0.07
     сім
    -0.06
    _PACK
    -0.06
     horr
    -0.06
    	Delete
    -0.06
     sab
    -0.06
    POSITIVE LOGITS
    """
↵
    0.07
    (marker
    0.07
    oral
    0.06
    اي
    0.06
    多
    0.06
    社区
    0.06
    صول
    0.06
    莉
    0.06
     wilderness
    0.06
    redo
    0.06
    Act Density 0.001%

    No Known Activations