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

    Neuronpedia

    INDEX
    Explanations

    agreements and contracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dvě
    0.44
     cabins
    0.43
    ждён
    0.42
     cottages
    0.42
    itten
    0.41
    eret
    0.41
    အတူ
    0.40
    ತ್ನ
    0.39
    ടിച്ചു
    0.39
     ऋषभ
    0.39
    POSITIVE LOGITS
     Referenced
    0.39
    त्व
    0.37
     heredit
    0.37
     ника
    0.37
     √
    0.37
    KEY
    0.36
     Instagram
    0.36
     Cuth
    0.36
     Inverse
    0.36
     Figma
    0.36
    Act Density 0.000%

    No Known Activations