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

    Neuronpedia

    INDEX
    Explanations

    setting blending superheroes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ofere
    0.42
     Polis
    0.42
    ípios
    0.41
     annotate
    0.40
     ofertas
    0.40
     diferenci
    0.39
     ofreci
    0.39
     polis
    0.39
    擾
    0.38
     medicamentos
    0.38
    POSITIVE LOGITS
    weather
    0.44
    graph
    0.41
    usd
    0.40
    版
    0.40
    eway
    0.39
    all
    0.39
    warehouse
    0.39
    orical
    0.39
     bych
    0.38
    pop
    0.38
    Act Density 0.000%

    No Known Activations