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

    Neuronpedia

    INDEX
    Explanations

    command

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    率
    -0.07
    rightarrow
    -0.06
    igate
    -0.06
    _products
    -0.06
     місті
    -0.06
    (score
    -0.06
    دان
    -0.06
     ferr
    -0.06
     Hercules
    -0.06
     RAD
    -0.06
    POSITIVE LOGITS
    超过
    0.07
    .“
    0.07
    qw
    0.07
    ebilirsiniz
    0.06
    atus
    0.06
    (internal
    0.06
     (__
    0.06
    uuml
    0.06
    \v
    0.06
     duo
    0.06
    Act Density 0.026%

    No Known Activations