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

    Neuronpedia

    INDEX
    Explanations

    can be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TMP
    -0.07
     "@"
    -0.06
    ính
    -0.06
    退出
    -0.06
    _big
    -0.06
     computers
    -0.06
    fir
    -0.06
     phận
    -0.06
     Saudis
    -0.05
    Special
    -0.05
    POSITIVE LOGITS
     oma
    0.08
     çoğ
    0.07
    cod
    0.07
    .Transport
    0.07
    �
    0.07
    覺
    0.07
     відч
    0.07
     representation
    0.06
    �
    0.06
    -expression
    0.06
    Act Density 0.020%

    No Known Activations