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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Herr
    -0.07
    _soup
    -0.06
    Invocation
    -0.06
    Seconds
    -0.06
    -messages
    -0.06
     herr
    -0.06
     fract
    -0.06
     Christie
    -0.06
    Variable
    -0.06
    -breaking
    -0.06
    POSITIVE LOGITS
    \'
    0.07
     crown
    0.06
     Readonly
    0.06
     ор
    0.06
     polov
    0.06
     correctness
    0.06
     utrecht
    0.06
    occup
    0.06
    (order
    0.06
    овж
    0.06
    Act Density 0.047%

    No Known Activations