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

    Neuronpedia

    INDEX
    Explanations

    it's not being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    0.45
     will
    0.42
     Initializes
    0.42
    D
    0.41
    s
    0.39
     Initial
    0.38
    m
    0.37
    initial
    0.36
    મ
    0.36
    will
    0.36
    POSITIVE LOGITS
     атмосфер
    0.44
     сущ
    0.44
     działal
    0.44
     ശേഷം
    0.44
     वैदिक
    0.43
     невозможно
    0.43
    calup
    0.43
     سلمان
    0.42
     discredit
    0.41
     роско
    0.41
    Act Density 0.000%

    No Known Activations