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

    Neuronpedia

    INDEX
    Explanations

    table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الفكر
    -0.08
    getParent
    -0.08
     assertion
    -0.07
    LIKE
    -0.07
    _num
    -0.07
     massive
    -0.07
     toggle
    -0.07
    <>();
↵
    -0.06
    odd
    -0.06
     fantasies
    -0.06
    POSITIVE LOGITS
    必要的
    0.08
     Cena
    0.07
    自愿
    0.07
     Habitat
    0.07
     yı
    0.07
     zostały
    0.07
     내가
    0.07
    Lua
    0.07
     hire
    0.07
    flat
    0.06
    Act Density 0.011%

    No Known Activations