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

    Neuronpedia

    INDEX
    Explanations

    ISO standards, Google Maps, specific queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ――――
    0.38
    Direct
    0.38
    槑
    0.37
     विशिष्ट
    0.36
    सान
    0.36
    ডার
    0.36
    درسة
    0.36
     Dark
    0.36
    Dark
    0.36
    暑
    0.36
    POSITIVE LOGITS
    Embed
    0.39
     கூற
    0.36
     zee
    0.36
     mys
    0.36
    ്യ
    0.35
     jang
    0.35
    자와
    0.35
     Eps
    0.35
    razio
    0.35
     لهم
    0.34
    Act Density 0.000%

    No Known Activations