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

    Neuronpedia

    INDEX
    Explanations

    common conversational starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     είναι
    1.22
    きた
    1.19
     vacío
    1.18
    ন
    1.17
     mô
    1.16
     μόνο
    1.16
     υπάρχει
    1.16
     personne
    1.15
     велоси
    1.15
     এসএম
    1.15
    POSITIVE LOGITS
    ز
    1.94
    a
    1.60
    d
    1.60
    y
    1.44
    У
    1.33
    و
    1.29
    os
    1.27
    de
    1.27
    so
    1.22
    da
    1.20
    Act Density 2.132%

    No Known Activations