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

    Neuronpedia

    INDEX
    Explanations

    verbs conjugated or forming nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ible
    0.62
    ಿರಿ
    0.54
    ly
    0.54
     Jupyter
    0.54
    irs
    0.51
    Integer
    0.51
     OneDrive
    0.50
    bir
    0.50
    ceptron
    0.49
    ful
    0.49
    POSITIVE LOGITS
    aciones
    1.11
    ación
    1.06
    ations
    1.05
    ating
    1.00
    azione
    0.97
    acion
    0.94
    ated
    0.93
    ACIÓN
    0.90
    ATIONS
    0.90
    ATING
    0.88
    Act Density 0.196%

    No Known Activations