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

    Neuronpedia

    INDEX
    Explanations

    lox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dod
    -0.07
     Presidential
    -0.07
     payable
    -0.07
     Respond
    -0.07
    .SelectCommand
    -0.06
    .Pe
    -0.06
     perennial
    -0.06
    Well
    -0.06
    amiliar
    -0.06
    угл
    -0.06
    POSITIVE LOGITS
    ῃ
    0.07
    aged
    0.07
    cją
    0.07
    灰尘
    0.07
    龛
    0.06
    潔
    0.06
    [group
    0.06
    анс
    0.06
    	job
    0.06
    zed
    0.06
    Act Density 0.001%

    No Known Activations