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

    Neuronpedia

    INDEX
    Explanations

    entity names and IDs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rése
    0.33
    playerPosition
    0.32
     hémorro
    0.32
    Missense
    0.32
    BtnFill
    0.32
    URNIZOR
    0.32
    hatiti
    0.31
    outheast
    0.31
    पीरियंस
    0.31
     রোধ
    0.30
    POSITIVE LOGITS
     name
    0.46
    name
    0.44
     and
    0.41
    ’
    0.37
    名称
    0.37
    '
    0.35
     이름
    0.34
     ID
    0.33
    名稱
    0.32
     uptime
    0.32
    Act Density 0.466%

    No Known Activations