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

    Neuronpedia

    INDEX
    Explanations

    generating letters, etc

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chat
    0.73
     Red
    0.69
    РС
    0.68
     col
    0.66
     Cal
    0.65
    itech
    0.65
     Yellow
    0.65
     Info
    0.65
     chatter
    0.63
     Chat
    0.63
    POSITIVE LOGITS
     Dreh
    0.89
    峦
    0.86
    ່າງ
    0.86
    Reached
    0.86
    stück
    0.85
    seq
    0.84
     रक्कम
    0.82
     장면
    0.81
     मागणी
    0.81
    örper
    0.81
    Act Density 0.051%

    No Known Activations