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

    Neuronpedia

    INDEX
    Explanations

    release

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oter
    -0.07
    긋
    -0.07
    akış
    -0.07
    趴在
    -0.07
    东海
    -0.07
     zx
    -0.07
    变成了
    -0.07
    tek
    -0.07
    口感
    -0.07
    ($"
    -0.06
    POSITIVE LOGITS
     restoring
    0.08
    ﰙ
    0.07
     Educ
    0.07
     circ
    0.07
     culturally
    0.07
    inv
    0.06
    clusão
    0.06
     utilized
    0.06
    idade
    0.06
    樵
    0.06
    Act Density 0.014%

    No Known Activations