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

    Neuronpedia

    INDEX
    Explanations

    location or state description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     রোগের
    0.35
     ಮೊದಲ
    0.35
    ᆼ
    0.35
     ១
    0.34
    Ž
    0.34
    >"
    0.34
    免疫
    0.33
    >
    0.33
    )=
    0.33
    失败
    0.33
    POSITIVE LOGITS
     Bolivia
    0.47
     You
    0.39
    <unused2176>
    0.38
     Your
    0.38
     इवन
    0.38
    വ്വ
    0.38
    <unused743>
    0.38
    <unused625>
    0.37
     вас
    0.37
    <unused398>
    0.36
    Act Density 0.003%

    No Known Activations