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

    Neuronpedia

    INDEX
    Explanations

    letter 'd' followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ColumnKind
    0.37
     tenga
    0.35
     نے
    0.34
     blew
    0.34
     saranno
    0.33
     differed
    0.33
     unterschied
    0.33
    ক্ক
    0.32
     aumentando
    0.31
     xlabel
    0.31
    POSITIVE LOGITS
     Crest
    0.36
     Overwatch
    0.35
     जो
    0.35
     concession
    0.33
     Dot
    0.32
     concessions
    0.32
     ലൈ
    0.32
    rosa
    0.31
     Lyme
    0.30
     totes
    0.30
    Act Density 0.004%

    No Known Activations