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

    Neuronpedia

    INDEX
    Explanations

    rate of change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.50
    Axis
    0.48
    Circle
    0.48
     Products
    0.46
    Action
    0.44
    Json
    0.43
    Prog
    0.43
    Bone
    0.42
    Abstract
    0.42
    uretics
    0.42
    POSITIVE LOGITS
    ﭼ
    0.46
     waktu
    0.44
     keluarga
    0.44
    ्यात
    0.43
     fes
    0.43
     Yed
    0.43
    座椅
    0.41
     daftar
    0.41
    だけで
    0.41
     aici
    0.40
    Act Density 0.002%

    No Known Activations