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

    Neuronpedia

    INDEX
    Explanations

    documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Й
    -0.07
    .uniform
    -0.07
     follows
    -0.07
     subscri
    -0.07
    Sc
    -0.07
     dict
    -0.06
     joins
    -0.06
     Dec
    -0.06
     persuaded
    -0.06
     contempt
    -0.06
    POSITIVE LOGITS
    .car
    0.07
    (stderr
    0.06
     AFL
    0.06
    entlich
    0.06
     маль
    0.06
     преп
    0.06
     промислов
    0.06
    netinet
    0.06
    ]='\
    0.06
    739
    0.06
    Act Density 0.001%

    No Known Activations