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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     наз
    -0.07
     подход
    -0.07
     เพราะ
    -0.06
    .HashSet
    -0.06
    게
    -0.06
    .encoding
    -0.06
     Colleg
    -0.06
     وزار
    -0.06
    .ForegroundColor
    -0.06
     Autor
    -0.06
    POSITIVE LOGITS
     vanilla
    0.06
    نی
    0.06
    افع
    0.06
     list
    0.06
    >',
    0.06
    entine
    0.06
    _TEM
    0.06
    USH
    0.06
     <*>
    0.06
    _elem
    0.06
    Act Density 0.000%

    No Known Activations