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

    Neuronpedia

    INDEX
    Explanations

    majority vote or rule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aliment
    0.42
     primaria
    0.42
    ª
    0.41
     Mata
    0.40
     peng
    0.40
     OSHA
    0.40
     alimentação
    0.39
     alimentación
    0.39
     entrada
    0.38
    ಅ
    0.38
    POSITIVE LOGITS
    itarian
    0.57
    majority
    0.50
     minority
    0.48
    itaria
    0.48
    Majority
    0.45
     majority
    0.44
    itaires
    0.43
     தம்
    0.43
     opinion
    0.42
     Majority
    0.42
    Act Density 0.005%

    No Known Activations