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

    Neuronpedia

    INDEX
    Explanations

    investigating suspicions or beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.53
     bravely
    0.47
     স
    0.44
     Xinhua
    0.41
     started
    0.40
    ية
    0.40
     heck
    0.40
    a
    0.39
     futhi
    0.39
     s
    0.39
    POSITIVE LOGITS
     Datos
    0.48
     Neces
    0.45
    Insect
    0.45
     модуля
    0.45
    ச்சூழ
    0.43
    Datos
    0.42
    Qty
    0.42
     datos
    0.42
    Declar
    0.42
    NIK
    0.41
    Act Density 0.000%

    No Known Activations