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

    Neuronpedia

    INDEX
    Explanations

    list or schedule

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    linkOpacity
    0.41
    ുമായി
    0.38
    charset
    0.38
    icrous
    0.37
    చిన
    0.37
    茱
    0.36
    aneo
    0.36
    ነት
    0.35
    ungk
    0.35
    ůj
    0.35
    POSITIVE LOGITS
    凝
    0.41
     STAR
    0.40
     flo
    0.39
    Saturday
    0.38
     Saturday
    0.37
     Sunday
    0.37
    Neal
    0.37
    litz
    0.36
    迷
    0.36
    Sunday
    0.36
    Act Density 0.000%

    No Known Activations