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

    Neuronpedia

    INDEX
    Explanations

    breakthroughs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    आर
    -0.08
    ਰਨ
    -0.08
    �
    -0.08
     adventurous
    -0.08
    टर
    -0.08
     diligent
    -0.08
    ान
    -0.08
     विव
    -0.07
    ‌ర
    -0.07
    र
    -0.07
    POSITIVE LOGITS
     breakthroughs
    0.10
    所在
    0.09
     हासिल
    0.08
     strides
    0.08
    usen
    0.08
    成果
    0.08
    cimento
    0.08
    uciones
    0.07
     erzielt
    0.07
    abla
    0.07
    Act Density 0.010%

    No Known Activations