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

    Neuronpedia

    INDEX
    Explanations

    ding ding Zap

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acte
    0.41
     erlebt
    0.36
     peritoneal
    0.36
    irli
    0.36
     maf
    0.36
     अनुबंध
    0.35
     affer
    0.35
     clip
    0.34
    .$,
    0.34
     phas
    0.34
    POSITIVE LOGITS
     Ding
    0.47
    ding
    0.46
     Hog
    0.46
    Ding
    0.44
    din
    0.42
    symbols
    0.42
    dings
    0.42
    Zap
    0.40
     arrows
    0.40
    redos
    0.39
    Act Density 4.620%

    No Known Activations