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

    Neuronpedia

    INDEX
    Explanations

    key design considerations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anál
    0.49
     Auswirkungen
    0.44
     stell
    0.43
     instância
    0.42
    셜
    0.42
     analisis
    0.42
     inoltre
    0.41
     diny
    0.41
     Lactobacillus
    0.41
     daje
    0.41
    POSITIVE LOGITS
    <0x89>
    0.51
    所有的
    0.49
    每个
    0.48
    aroni
    0.47
    那么多
    0.46
     κάθε
    0.43
     قبر
    0.42
    們
    0.42
    ทุก
    0.41
    Expr
    0.40
    Act Density 0.009%

    No Known Activations