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

    Neuronpedia

    INDEX
    Explanations

    technical documentation or code examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     customizations
    0.52
     fruto
    0.49
     FontSize
    0.47
     aplicativos
    0.47
     carbons
    0.47
    Ꮸ
    0.46
     売場面積
    0.45
    bufs
    0.45
     carts
    0.45
     интеллек
    0.44
    POSITIVE LOGITS
     d
    0.54
    0.52
     de
    0.49
     n
    0.48
    Ré
    0.48
     v
    0.48
    ---
    0.47
     nej
    0.46
     moindre
    0.46
     dele
    0.45
    Act Density 0.001%

    No Known Activations