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

    Neuronpedia

    INDEX
    Explanations

    situation descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ються
    0.46
    гно
    0.43
     straightforward
    0.43
    ряда
    0.42
     delivery
    0.42
    ниця
    0.40
     back
    0.39
    arak
    0.39
     coated
    0.39
    ↵↵
    0.39
    POSITIVE LOGITS
     你
    0.54
    elementProp
    0.52
    魷
    0.47
     queryObject
    0.46
    ጥረ
    0.46
    ProxyAgent
    0.44
     Log
    0.43
    Loy
    0.43
    Electron
    0.42
     siguiendo
    0.42
    Act Density 0.000%

    No Known Activations