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

    Neuronpedia

    INDEX
    Explanations

    recipes for baked goods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     výraz
    0.53
     větš
    0.48
     فيها
    0.44
     هناك
    0.43
     Hrvatskoj
    0.42
     ấm
    0.41
     Fußball
    0.40
    éci
    0.40
     Ekim
    0.40
    ká
    0.40
    POSITIVE LOGITS
    ber
    0.51
    model
    0.50
    मूर्ति
    0.48
    ases
    0.48
    Model
    0.48
     モデル
    0.48
    𝑺
    0.48
    𝑬
    0.47
    𝒕
    0.47
    asha
    0.47
    Act Density 0.001%

    No Known Activations