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

    Neuronpedia

    INDEX
    Explanations

    prompt engineering and ai prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rupani
    0.41
     grafico
    0.41
    τού
    0.40
     animasi
    0.40
    gitian
    0.39
     reprezent
    0.39
     calcula
    0.39
    ټ
    0.39
    义
    0.39
     appliquer
    0.38
    POSITIVE LOGITS
     negative
    0.62
    negative
    0.61
     positive
    0.60
    Negative
    0.60
    Prompt
    0.60
     Prompt
    0.60
     Negative
    0.59
     нега
    0.57
    Positive
    0.57
    prompt
    0.56
    Act Density 0.039%

    No Known Activations