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

    Neuronpedia

    INDEX
    Explanations

    explaining function or status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ステル
    0.42
    hierarchy
    0.40
    Hierarchy
    0.39
    უფ
    0.39
    Patch
    0.38
    urie
    0.38
    Heinrich
    0.38
    ଶ
    0.38
    Categoria
    0.38
    ヒ
    0.37
    POSITIVE LOGITS
     unloaded
    0.46
     loaded
    0.43
     qualities
    0.42
     easy
    0.41
     utilizes
    0.40
     readings
    0.39
     projects
    0.39
     offered
    0.39
     persists
    0.39
     broadened
    0.39
    Act Density 0.004%

    No Known Activations