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

    Neuronpedia

    INDEX
    Explanations

    linked list operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lineare
    0.42
     Figura
    0.41
     efectivo
    0.40
     fechas
    0.40
    招待
    0.39
     ريد
    0.39
     rejects
    0.39
     linearly
    0.39
     puree
    0.39
     liczba
    0.38
    POSITIVE LOGITS
     Thumb
    0.43
     disconnect
    0.43
    Substitute
    0.42
    Thumb
    0.42
    cut
    0.40
    Position
    0.39
    families
    0.39
    position
    0.39
     his
    0.39
     समाजसेवी
    0.39
    Act Density 0.012%

    No Known Activations