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

    Neuronpedia

    INDEX
    Explanations

    "here's a breakdown"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Maximize
    0.47
    Particles
    0.46
    мо
    0.46
    О
    0.46
    这些
    0.46
     aceste
    0.46
    代码
    0.45
    别人
    0.44
    дите
    0.44
    Про
    0.44
    POSITIVE LOGITS
    available
    0.46
    rican
    0.43
    agan
    0.42
     उपलब्ध
    0.42
     available
    0.42
    chn
    0.41
    ida
    0.41
    itan
    0.41
    thia
    0.41
    cca
    0.41
    Act Density 0.002%

    No Known Activations