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

    Neuronpedia

    INDEX
    Explanations

    worry about provisioning, upgrading, costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    지만
    0.70
    ный
    0.69
    ي
    0.65
    рь
    0.64
     опыта
    0.64
    ные
    0.64
    ната
    0.64
    ныя
    0.63
    льт
    0.62
     както
    0.59
    POSITIVE LOGITS
     n
    0.73
     end
    0.68
     ink
    0.66
     y
    0.63
    ell
    0.63
     o
    0.62
    h
    0.62
     on
    0.61
    p
    0.60
    ാന്‍
    0.59
    Act Density 0.010%

    No Known Activations