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

    Neuronpedia

    INDEX
    Explanations

    lucky break or lucky enough

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    讧
    2.70
     autant
    2.45
    ض
    2.41
     Commit
    2.40
    𝚝
    2.38
    人员
    2.36
     nouvelles
    2.33
     жаса
    2.32
     thoroughly
    2.31
    ible
    2.31
    POSITIVE LOGITS
     aro
    2.58
     света
    2.52
    čil
    2.48
    ്
    2.34
    शाली
    2.29
     romana
    2.25
     área
    2.24
     gypsum
    2.23
    🤞
    2.20
     ক্রমে
    2.20
    Act Density 0.019%

    No Known Activations