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

    Neuronpedia

    INDEX
    Explanations

    LLM concept and safety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ía
    0.50
    ie
    0.47
    stri
    0.46
    ética
    0.46
    atia
    0.45
    ándola
    0.44
    wala
    0.44
    acca
    0.44
    গি
    0.43
    !’
    0.42
    POSITIVE LOGITS
     Volkswagen
    0.52
    ต
    0.52
    เฉพาะ
    0.51
    オーナー
    0.51
     Hitler
    0.49
    म्यान
    0.49
     именем
    0.48
    नंतर
    0.48
     обозна
    0.47
     Fallout
    0.47
    Act Density 0.001%

    No Known Activations