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

    Neuronpedia

    INDEX
    Explanations

    applications and situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     et
    0.43
     succinct
    0.43
     عن
    0.42
    с
    0.41
     comisión
    0.40
    躇
    0.40
     ripening
    0.40
     für
    0.39
    сия
    0.39
    rição
    0.39
    POSITIVE LOGITS
    is
    0.50
    h
    0.45
    에서는
    0.45
    eve
    0.42
    에서도
    0.41
     purposes
    0.39
    rish
    0.39
    ่
    0.39
    ฟ
    0.38
    Fig
    0.37
    Act Density 1.161%

    No Known Activations