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

    Neuronpedia

    INDEX
    Explanations

    testing to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ください
    2.14
     attrib
    1.91
    querque
    1.89
    笪
    1.84
     ternyata
    1.80
    صور
    1.80
    يير
    1.80
     ottenuto
    1.79
     Dioc
    1.77
    র
    1.74
    POSITIVE LOGITS
     Titans
    1.90
    aments
    1.86
     Tots
    1.80
    estries
    1.76
    िणी
    1.75
    ekwondo
    1.74
     Terror
    1.73
    isches
    1.70
     Troubles
    1.69
     Tack
    1.69
    Act Density 2.584%

    No Known Activations