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

    Neuronpedia

    INDEX
    Explanations

    templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tipi
    0.37
     téléphonique
    0.35
     indulgent
    0.34
    <0xBE>
    0.34
    תו
    0.34
     исследова
    0.33
    ке
    0.33
     accidental
    0.33
    ເປັນ
    0.33
     aiutare
    0.33
    POSITIVE LOGITS
    et
    0.65
    z
    0.56
    L
    0.50
    k
    0.50
    X
    0.50
    at
    0.49
    Text
    0.49
    Message
    0.49
    Elementos
    0.48
    W
    0.48
    Act Density 0.008%

    No Known Activations