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

    Neuronpedia

    INDEX
    Explanations

    prompt engineering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     возможность
    0.55
     сможет
    0.50
    ),
    0.50
     করলো
    0.49
     yerine
    0.47
     apartamentos
    0.46
    可能性がある
    0.45
     pessoal
    0.45
     werd
    0.44
     했
    0.44
    POSITIVE LOGITS
    ühm
    0.50
    ناول
    0.49
     eponym
    0.48
    螓
    0.48
     inspiring
    0.46
     Unlock
    0.45
     القرن
    0.44
    依托
    0.43
    Unlock
    0.43
     skyrocketing
    0.43
    Act Density 0.008%

    No Known Activations