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

    Neuronpedia

    INDEX
    Explanations

    generally, usually, often

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.57
     energies
    0.48
     kom
    0.48
     energ
    0.47
     frit
    0.47
     energi
    0.46
     dick
    0.46
     ED
    0.46
     default
    0.45
     charm
    0.45
    POSITIVE LOGITS
     문화
    0.61
     주변
    0.59
     보통
    0.52
    бычно
    0.49
     마치
    0.48
     ብዙውን
    0.48
    <unused99>
    0.48
    ήθ
    0.48
     가까
    0.47
     சார்பில்
    0.46
    Act Density 0.000%

    No Known Activations