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

    Neuronpedia

    INDEX
    Explanations

    the war of the roses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    there
    0.51
    exact
    0.50
    continued
    0.50
    lerin
    0.49
    community
    0.48
     ملک
    0.48
    complicated
    0.48
    pecial
    0.47
    dari
    0.47
    joint
    0.47
    POSITIVE LOGITS
    屻
    0.50
    Ice
    0.48
    虽然
    0.46
     Ice
    0.45
    语
    0.45
    冰
    0.44
    acide
    0.43
    既然
    0.43
     naturally
    0.42
     Filme
    0.42
    Act Density 0.008%

    No Known Activations