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

    Neuronpedia

    INDEX
    Explanations

    Strategic planning and specific areas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ...?
    0.46
    Light
    0.45
    ඥ
    0.44
    OG
    0.44
     મિત
    0.44
     ROM
    0.43
    )?;
    0.43
     दौड़
    0.43
    Running
    0.43
    High
    0.42
    POSITIVE LOGITS
    ingos
    0.54
    juang
    0.49
    nq
    0.49
    שא
    0.46
    ्च
    0.46
    өл
    0.46
    Jx
    0.46
     Верхов
    0.45
    ajno
    0.44
    ми
    0.44
    Act Density 0.001%

    No Known Activations