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

    Neuronpedia

    INDEX
    Explanations

    automatic abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Jakarta
    0.44
    機
    0.44
     estética
    0.44
     evitare
    0.43
    LEGISLATIVE
    0.42
     Limits
    0.41
     scopo
    0.41
     طريق
    0.41
    Malaysia
    0.41
    verlag
    0.40
    POSITIVE LOGITS
    ූර්
    0.53
    ె
    0.48
    sembles
    0.47
    ей
    0.47
    样的
    0.46
     инструмента
    0.45
    oloj
    0.44
    ин
    0.43
    olver
    0.43
    ταν
    0.43
    Act Density 0.000%

    No Known Activations