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

    Neuronpedia

    INDEX
    Explanations

    contrast or negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.56
    ocken
    0.46
    edited
    0.46
    no
    0.46
    of
    0.45
    items
    0.43
    activities
    0.43
    ingresso
    0.43
     items
    0.43
    ellt
    0.43
    POSITIVE LOGITS
    ನ್ಸ್
    0.46
    టర్
    0.45
     hợp
    0.44
     전류
    0.43
     تصویر
    0.43
     شك
    0.43
     అంత
    0.42
     Unterstützung
    0.42
    อกาส
    0.42
    Fermi
    0.41
    Act Density 0.001%

    No Known Activations