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

    Neuronpedia

    INDEX
    Explanations

    LaTeX table of contents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RESPONS
    -0.08
     głów
    -0.07
     Exceptions
    -0.07
     stochastic
    -0.07
    .Task
    -0.07
    puty
    -0.07
    都很
    -0.07
     Flash
    -0.07
     HALF
    -0.07
    _PR
    -0.07
    POSITIVE LOGITS
     Bram
    0.07
    \'
    0.06
    za
    0.06
     الأخير
    0.06
     מראש
    0.06
    \")
    0.06
     crea
    0.06
    roma
    0.06
    因地制
    0.06
     simulate
    0.06
    Act Density 0.001%

    No Known Activations