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

    Neuronpedia

    INDEX
    Explanations

    version numbers in configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.51
    ي
    0.50
    NameTo
    0.49
    ファイルの
    0.49
    髡
    0.49
    されていない
    0.47
    ם
    0.46
     целью
    0.46
     Daten
    0.46
    颓
    0.45
    POSITIVE LOGITS
     hybrid
    0.54
     with
    0.50
     technology
    0.49
     mold
    0.48
     simplified
    0.48
     doubles
    0.46
     modell
    0.46
     mécan
    0.46
     midfield
    0.46
    2
    0.45
    Act Density 0.010%

    No Known Activations