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

    Neuronpedia

    INDEX
    Explanations

    AI Studio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ahead
    0.42
    浪
    0.38
     cycle
    0.38
     গম
    0.38
     ahead
    0.38
    scope
    0.38
    σια
    0.37
     बैंकों
    0.37
     hump
    0.37
    Ahead
    0.37
    POSITIVE LOGITS
     Ap
    0.41
    StoreException
    0.39
     ap
    0.39
     Timberlake
    0.39
     Galle
    0.37
     bah
    0.37
    巽
    0.36
    والی
    0.36
    VSLU
    0.36
     exhibition
    0.35
    Act Density 0.004%

    No Known Activations