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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skj
    0.72
     Hammers
    0.68
     sols
    0.66
    athy
    0.65
    сона
    0.64
    ithmetic
    0.63
    危害
    0.63
    ismuth
    0.63
     स्किन
    0.63
     Pelham
    0.63
    POSITIVE LOGITS
     ర
    0.71
     r
    0.65
     стру
    0.63
     violin
    0.63
    க்கர
    0.63
     Space
    0.61
     Ese
    0.61
    ，”
    0.60
     $*$
    0.60
    䇝
    0.59
    Act Density 0.001%

    No Known Activations