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

    Neuronpedia

    INDEX
    Explanations

    upsides, upselling, upskilling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     হানাদার
    0.70
    vate
    0.69
     bedtime
    0.67
     szyb
    0.67
    ৎস্য
    0.64
    ních
    0.64
     pitanje
    0.64
    to
    0.64
     regenerated
    0.64
    vand
    0.64
    POSITIVE LOGITS
    WING
    0.82
     ups
    0.80
    Wing
    0.75
    urne
    0.74
    графии
    0.74
     Mazz
    0.73
     চরিত
    0.71
     exclusivos
    0.71
    IDE
    0.70
    Aless
    0.70
    Act Density 0.004%

    No Known Activations