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

    Neuronpedia

    INDEX
    Explanations

    actual outcome or result

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hebat
    0.36
     amd
    0.34
     kvůli
    0.34
     similaires
    0.34
     persiapan
    0.34
     similaire
    0.33
     avevano
    0.32
     datafile
    0.32
     lej
    0.32
     pernah
    0.31
    POSITIVE LOGITS
     correspondingly
    0.46
     vervolgens
    0.42
     ACTUAL
    0.40
    শেষে
    0.40
     natomiast
    0.38
     οποία
    0.37
    actual
    0.36
     말미암아
    0.36
    実際に
    0.35
    ವನ್ನು
    0.35
    Act Density 0.281%

    No Known Activations