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

    Neuronpedia

    INDEX
    Explanations

    java programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒈬
    0.49
     Акы
    0.48
    थोरो
    0.47
    𒌅
    0.46
     स्प्रे
    0.45
    securityMarks
    0.44
    textepsilon
    0.44
    WMat
    0.44
    angleOf
    0.44
    avkh
    0.44
    POSITIVE LOGITS
    ;
    0.85
    .
    0.53
    ,
    0.51
    ；
    0.50
    }
    0.50
    -
    0.48
    ();
    0.47
        
    0.46
     ;
    0.43
    )
    0.43
    Act Density 0.004%

    No Known Activations