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

    Neuronpedia

    INDEX
    Explanations

    blocks trackers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bun
    0.43
    Lod
    0.41
     Lod
    0.39
    🚃
    0.38
    ীয়
    0.38
     চিহ্নিত
    0.37
     Static
    0.37
    Weight
    0.36
     therefrom
    0.36
    校验
    0.36
    POSITIVE LOGITS
     releg
    0.39
     reservados
    0.37
     ask
    0.37
     déplacer
    0.37
     stores
    0.35
     só
    0.35
     enable
    0.34
     оста
    0.33
     creases
    0.33
    មុ
    0.33
    Act Density 0.000%

    No Known Activations