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

    Neuronpedia

    INDEX
    Explanations

    vs, Versus, VS Code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ান্ড
    0.43
     pozitiv
    0.43
     tos
    0.42
    老師
    0.42
     підтрим
    0.41
    屇
    0.40
     Duplicate
    0.39
     supports
    0.38
     Denote
    0.38
     రూ
    0.38
    POSITIVE LOGITS
    auce
    0.51
     VS
    0.47
    VS
    0.43
    enterprise
    0.43
     vers
    0.43
     Versus
    0.42
     vs
    0.42
     verse
    0.41
     versa
    0.41
     VERS
    0.40
    Act Density 0.010%

    No Known Activations