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

    Neuronpedia

    INDEX
    Explanations

    effort level: High

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     enriching
    0.42
     enriqu
    0.41
     Enrich
    0.39
    wendungs
    0.39
     도와
    0.39
    <0x99>
    0.38
    formas
    0.38
    утбу
    0.38
     interesantes
    0.37
    ື່ອງ
    0.37
    POSITIVE LOGITS
     sans
    0.41
     past
    0.40
     Vid
    0.40
     High
    0.38
    ؛
    0.38
     Vil
    0.38
     Belediyesi
    0.38
     Mechanics
    0.37
    shall
    0.37
     edits
    0.37
    Act Density 0.002%

    No Known Activations