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

    Neuronpedia

    INDEX
    Explanations

    I say

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Z
    0.75
    ?
    0.75
    ่
    0.71
    IC
    0.71
    M
    0.71
     The
    0.70
    SR
    0.70
    ↵
    0.69
     A
    0.69
    CA
    0.68
    POSITIVE LOGITS
     syph
    0.60
    ொழுது
    0.60
     abdomin
    0.60
     شوند
    0.59
     extravagant
    0.59
     creepy
    0.58
     سعيد
    0.58
     كثير
    0.57
     wickedness
    0.57
    ફેદ
    0.57
    Act Density 0.000%

    No Known Activations