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

    Neuronpedia

    INDEX
    Explanations

    scientific studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    더
    -0.07
     FRIEND
    -0.06
    جات
    -0.06
     '/',↵
    -0.06
     Modification
    -0.06
    Ter
    -0.06
      
↵
    -0.06
     nonzero
    -0.06
     عام
    -0.06
     Retrieve
    -0.06
    POSITIVE LOGITS
    IPS
    0.07
     niños
    0.06
     rats
    0.06
     legis
    0.06
    (bool
    0.06
    输
    0.06
    ，为
    0.06
     m
    0.06
    _free
    0.06
    _age
    0.06
    Act Density 0.058%

    No Known Activations