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

    Neuronpedia

    INDEX
    Explanations

    combining or switching state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᡧ
    0.53
    یه
    0.49
    ер
    0.48
     بۇ
    0.44
    anke
    0.43
    ò
    0.43
     asing
    0.43
    ільки
    0.41
     sådan
    0.41
    ecological
    0.40
    POSITIVE LOGITS
    CTIONS
    0.48
     presenceData
    0.43
    controls
    0.42
    豁
    0.42
    LAGS
    0.42
    ments
    0.41
    LLO
    0.40
    מד
    0.40
     to
    0.40
    men
    0.40
    Act Density 0.001%

    No Known Activations