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

    Neuronpedia

    INDEX
    Explanations

    martin or mart names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你要
    0.37
    ៅ
    0.37
    trees
    0.36
     planned
    0.36
    鈳
    0.36
    犄
    0.35
    計劃
    0.35
    㳻
    0.35
     Overnight
    0.35
    aturi
    0.34
    POSITIVE LOGITS
     inertial
    0.46
    olom
    0.45
    ingale
    0.44
    MART
    0.43
     പേ
    0.42
    inert
    0.41
     mart
    0.40
     MART
    0.40
     cập
    0.40
     occupation
    0.39
    Act Density 0.007%

    No Known Activations