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

    Neuronpedia

    INDEX
    Explanations

    Teaching positions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yan
    -0.07
    _servers
    -0.06
     FW
    -0.06
     problemas
    -0.06
    单位
    -0.06
     Lamb
    -0.06
     Kum
    -0.06
     Roh
    -0.06
     Jugend
    -0.06
    (existing
    -0.06
    POSITIVE LOGITS
    Đ
    0.07
     espec
    0.07
    iples
    0.07
     та
    0.07
     invo
    0.07
     trous
    0.06
    orney
    0.06
    but
    0.06
    -aos
    0.06
    uze
    0.06
    Act Density 0.050%

    No Known Activations