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

    Neuronpedia

    INDEX
    Explanations

    mathematical or symbolic expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bed
    0.49
    ベット
    0.47
    bed
    0.45
    高速
    0.39
    Contacto
    0.39
     Bed
    0.39
     bed
    0.38
    認定
    0.37
    Ji
    0.37
    ⓜ
    0.36
    POSITIVE LOGITS
     avoid
    0.46
     избежать
    0.42
     evitare
    0.40
     evitar
    0.39
     Avoid
    0.38
     kaç
    0.38
     Shay
    0.37
     Scalars
    0.37
    避免
    0.36
     wahrscheinlich
    0.36
    Act Density 0.050%

    No Known Activations