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

    Neuronpedia

    INDEX
    Explanations

    theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uese
    -0.26
     markdown
    -0.25
    inati
    -0.25
    ULK
    -0.25
     claimed
    -0.25
    PEG
    -0.25
    ues
    -0.25
    åĽĽä¸ªæĦıè¯Ĩ
    -0.25
    ifest
    -0.25
    UES
    -0.24
    POSITIVE LOGITS
    elem
    0.28
    Transparent
    0.27
    峪
    0.26
    袢
    0.26
    -zone
    0.25
    _tl
    0.25
     looping
    0.25
     Province
    0.25
    éļıæľº
    0.25
    -clock
    0.24
    Act Density 0.004%

    No Known Activations