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

    Neuronpedia

    INDEX
    Explanations

    python code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ✠
    0.37
     downstairs
    0.36
    Durham
    0.36
    นักงาน
    0.35
     प्रीम
    0.35
    geschoss
    0.35
    owania
    0.34
    Manchester
    0.34
    Stanley
    0.34
     பிச்சு
    0.34
    POSITIVE LOGITS
    ulang
    0.43
    준다
    0.38
     exemplo
    0.38
     숨
    0.36
    片段
    0.36
     sekitar
    0.36
     elaborado
    0.35
    嬋
    0.35
     sociedad
    0.35
     yakin
    0.35
    Act Density 0.020%

    No Known Activations