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

    Neuronpedia

    INDEX
    Explanations

    math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蝶
    -0.08
     gospodar
    -0.08
    发行
    -0.08
    Starter
    -0.08
    TH
    -0.08
     redistribution
    -0.08
    itionen
    -0.08
     Berkshire
    -0.07
    =item
    -0.07
     വിത
    -0.07
    POSITIVE LOGITS
     distances
    0.12
     दूरी
    0.11
    距离
    0.11
     Distance
    0.10
     afstand
    0.10
     расстоя
    0.10
     distance
    0.10
    hattan
    0.09
     Manhattan
    0.09
     puck
    0.09
    Act Density 0.043%

    No Known Activations