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

    Neuronpedia

    INDEX
    Explanations

    closing parenthesis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ടുത
    0.43
    laug
    0.41
    ások
    0.41
    actionBarTab
    0.40
    Metaxy
    0.40
    ന്തപു
    0.40
    يديو
    0.39
     undisturbed
    0.39
     ね
    0.38
    нето
    0.38
    POSITIVE LOGITS
     Gir
    0.48
    ‎
    0.42
    AM
    0.40
    OF
    0.40
     Sal
    0.39
     Office
    0.39
     Tr
    0.39
     Ed
    0.39
    Sp
    0.39
     C
    0.38
    Act Density 0.002%

    No Known Activations