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

    Neuronpedia

    INDEX
    Explanations

    Dallas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conservative
    -0.07
    time
    -0.07
    .dim
    -0.07
    ꦇ
    -0.07
    -messages
    -0.07
    能够在
    -0.07
     whereas
    -0.06
    ()["
    -0.06
     mừng
    -0.06
    (`↵
    -0.06
    POSITIVE LOGITS
    횔
    0.07
    _ll
    0.07
    ONS
    0.07
     проц
    0.06
     neces
    0.06
    _modifier
    0.06
    _integral
    0.06
    од
    0.06
    CLA
    0.06
     должна
    0.06
    Act Density 0.000%

    No Known Activations