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

    Neuronpedia

    INDEX
    Explanations

    due to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    any
    0.51
     cualquiera
    0.46
     any
    0.45
     ANY
    0.44
    ANY
    0.44
    理由は
    0.42
    inos
    0.42
     cualquier
    0.42
    原因是
    0.41
     kerana
    0.41
    POSITIVE LOGITS
     advances
    0.58
     confidentiality
    0.58
     Advances
    0.57
     محدود
    0.57
     advancements
    0.54
    Advances
    0.52
     similarities
    0.52
     extensive
    0.50
     ограничен
    0.50
     Considerable
    0.48
    Act Density 0.010%

    No Known Activations