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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تصوير
    -0.08
    겥
    -0.07
    ecn
    -0.07
     números
    -0.07
     telemetry
    -0.07
    וצרים
    -0.07
     נותן
    -0.07
     acesso
    -0.07
     UNITY
    -0.06
     Unternehmen
    -0.06
    POSITIVE LOGITS
    𝗔
    0.07
     Kat
    0.07
    '=>['
    0.07
     Л
    0.07
     sinister
    0.07
    ');↵↵
    0.06
    浩
    0.06
    ');↵
    0.06
     Ava
    0.06
    "];↵
    0.06
    Act Density 0.011%

    No Known Activations