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

    Neuronpedia

    INDEX
    Explanations

    dialogue breaks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    1.20
    s
    1.10
     the
    1.01
     this
    0.92
    sport
    0.91
    vät
    0.89
    pflicht
    0.88
    cemment
    0.86
     your
    0.84
     REGIUNI
    0.83
    POSITIVE LOGITS
    ี
    1.26
    ↵↵
    1.14
    ized
    1.02
    并非
    0.88
     Of
    0.87
    ️⃣
    0.86
    ()=>{
    0.85
    ']].
    0.85
    나
    0.85
    つの
    0.83
    Act Density 0.001%

    No Known Activations