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

    Neuronpedia

    INDEX
    Explanations

    time or state transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VR
    0.54
    FIFO
    0.49
    omen
    0.47
    conjug
    0.47
    メカ
    0.46
    ゲ
    0.46
    PDF
    0.46
    acion
    0.45
    BD
    0.45
    Czas
    0.45
    POSITIVE LOGITS
     său
    0.50
     BEEN
    0.48
    ड़ियों
    0.48
     Policía
    0.48
     создал
    0.46
    بيوتر
    0.45
     wł
    0.44
     hôtel
    0.44
     millió
    0.44
     bày
    0.44
    Act Density 0.003%

    No Known Activations