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

    Neuronpedia

    INDEX
    Explanations

    Supreme

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sock
    -0.09
    UFF
    -0.07
    匕
    -0.07
    лект
    -0.07
    uf
    -0.07
     Utt
    -0.07
    zx
    -0.07
    統
    -0.07
    ulatory
    -0.07
    不由
    -0.07
    POSITIVE LOGITS
    ⚃
    0.07
    智能手机
    0.07
    私が
    0.07
    ߌ
    0.07
    首创
    0.07
    !</
    0.07
    ')}</
    0.07
     exquisite
    0.07
    %">↵
    0.07
    נציג
    0.06
    Act Density 0.002%

    No Known Activations