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

    Neuronpedia

    INDEX
    Explanations

    comparison or versus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    łow
    0.41
    𝐧
    0.39
    డు
    0.38
     रुका
    0.37
     тъ
    0.37
    <unused749>
    0.37
     nhất
    0.37
    只
    0.37
    પૂર્ણ
    0.36
    เดิม
    0.36
    POSITIVE LOGITS
     compared
    1.56
     versus
    1.43
    Compared
    1.39
     vs
    1.34
     Compared
    1.34
     unlike
    1.31
    compared
    1.30
    相比
    1.30
    versus
    1.20
     Versus
    1.19
    Act Density 0.310%

    No Known Activations