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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     Manson
    -0.07
    起来
    -0.07
    _ME
    -0.06
    昇
    -0.06
    ERSHEY
    -0.06
    ře
    -0.06
    doors
    -0.06
     Weg
    -0.06
    _changes
    -0.06
    POSITIVE LOGITS
    智能
    0.07
     amongst
    0.07
    $status
    0.06
     distinctive
    0.06
    .Customer
    0.06
    _INCLUDE
    0.06
     dõi
    0.06
    	elseif
    0.06
    .setVisible
    0.06
     Fantasy
    0.06
    Act Density 0.002%

    No Known Activations