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

    Neuronpedia

    INDEX
    Explanations

    modal verbs followed by conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     använder
    0.29
     devons
    0.29
     brainstorming
    0.29
     petting
    0.29
     pressing
    0.28
     pecados
    0.28
     muốn
    0.27
     utilisons
    0.27
     documentación
    0.27
     parsing
    0.27
    POSITIVE LOGITS
     be
    0.52
     essere
    0.39
     undoubtedly
    0.37
     not
    0.37
     result
    0.36
     быть
    0.35
    be
    0.34
    result
    0.32
     constitute
    0.32
     remain
    0.32
    Act Density 0.021%

    No Known Activations