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

    Neuronpedia

    INDEX
    Explanations

    -minute

    np_max-act-logits · gemini-2.0-flashTriggered by @bettyfeng2003
    New Auto-Interp
    Negative Logits
    𝜋
    -0.07
     ngu
    -0.07
    酴
    -0.07
     blossom
    -0.07
    갭
    -0.07
     componentDidUpdate
    -0.06
    inx
    -0.06
     Hale
    -0.06
    👶
    -0.06
    是有
    -0.06
    POSITIVE LOGITS
    源泉
    0.07
     records
    0.07
    ']:↵
    0.07
    _Read
    0.07
    河北省
    0.07
     recommend
    0.06
     submitted
    0.06
     economical
    0.06
     המון
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations