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

    Neuronpedia

    INDEX
    Explanations

    code comments and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     사용할
    0.58
     huh
    0.58
     지난
    0.57
     ”
    0.55
    ुलेंस
    0.52
     downside
    0.52
     optima
    0.52
     omnip
    0.52
     확인할
    0.51
     residency
    0.51
    POSITIVE LOGITS
    謃
    0.59
    <unused753>
    0.53
     edildi
    0.49
     करके
    0.48
     reformas
    0.47
     itu
    0.46
     Потому
    0.46
     localización
    0.46
     sorpresa
    0.45
    <unused2135>
    0.44
    Act Density 1.284%

    No Known Activations