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

    Neuronpedia

    INDEX
    Explanations

    code blocks and multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    dicke
    0.47
    aws
    0.42
    хих
    0.41
     وزیر
    0.40
    :'',
    0.39
    young
    0.39
     Dict
    0.39
    eem
    0.39
    ccak
    0.39
    ma
    0.39
    POSITIVE LOGITS
     Vous
    0.57
     můžete
    0.49
     <?
    0.47
     artículos
    0.47
     That
    0.46
     situazione
    0.46
     Você
    0.46
     puoi
    0.45
     você
    0.45
     puedes
    0.44
    Act Density 0.037%

    No Known Activations