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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and emotions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SYSTEM
    0.47
    Solve
    0.45
    ${
    0.43
    暐
    0.43
     Deux
    0.43
    系统
    0.42
     Hunde
    0.42
    嚿
    0.41
    侓
    0.41
    Synth
    0.41
    POSITIVE LOGITS
    ında
    0.52
    ERON
    0.46
    namefont
    0.45
     crian
    0.44
    লাইয়া
    0.43
    ه‌
    0.41
    oflav
    0.41
    рования
    0.40
     እና
    0.40
    ستانی
    0.40
    Act Density 0.000%

    No Known Activations