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

    Neuronpedia

    INDEX
    Explanations

    row , height , acres

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Нет
    0.39
    Todd
    0.37
    ኪያ
    0.36
     compromised
    0.36
     Laut
    0.36
     programmable
    0.36
     BlueprintName
    0.35
    Todo
    0.35
     IPTV
    0.35
    铖
    0.35
    POSITIVE LOGITS
     spy
    0.44
     row
    0.43
    운
    0.39
    rystal
    0.38
     स्तंभ
    0.38
     acres
    0.37
    row
    0.37
     TRA
    0.37
     행
    0.37
     rows
    0.36
    Act Density 0.000%

    No Known Activations