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

    Neuronpedia

    INDEX
    Explanations

    Will:Protocol:prevents:nature:generations:mentions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    局
    0.45
     lumps
    0.42
    역
    0.42
    器
    0.41
    IELD
    0.40
     flavored
    0.40
     *
    0.39
    TACT
    0.39
    ية
    0.39
    SIMPLE
    0.39
    POSITIVE LOGITS
     नौकरी
    0.45
     αγ
    0.44
    颂
    0.44
     Raquel
    0.43
     संगठ
    0.42
     प्रा
    0.42
     પ્રા
    0.42
     Sı
    0.42
     cooperación
    0.41
     помога
    0.41
    Act Density 0.004%

    No Known Activations