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

    Neuronpedia

    INDEX
    Explanations

    code, services, and schemas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     écologique
    0.42
     Wochschr
    0.40
     bitOp
    0.38
    调节
    0.38
    峠
    0.37
    貘
    0.37
    曛
    0.37
     فونٹ
    0.37
    燃烧
    0.36
    釭
    0.36
    POSITIVE LOGITS
    if
    0.44
    ↵↵
    0.44
     not
    0.44
    ↵↵↵
    0.43
      
    0.40
    ret
    0.40
    }
    0.40
    ↵
    0.40
     as
    0.40
    with
    0.39
    Act Density 0.012%

    No Known Activations