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

    Neuronpedia

    INDEX
    Explanations

    label/key phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     alan
    0.67
     primaire
    0.66
     here
    0.65
     hier
    0.63
     무엇
    0.62
    幹
    0.61
     ancestry
    0.60
     ვ
    0.58
     maneuvers
    0.58
    苫
    0.58
    POSITIVE LOGITS
    Trials
    0.74
    >≤</
    0.74
     ఇచ్చ
    0.71
    +"/"+
    0.70
    Parser
    0.69
    ன்பது
    0.68
    +(
    0.68
    &(
    0.66
    /<
    0.66
    >+</
    0.65
    Act Density 0.112%

    No Known Activations