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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Delay
    -0.06
     pin
    -0.06
     Trust
    -0.06
     feet
    -0.06
    yas
    -0.06
     Dragon
    -0.06
    _spi
    -0.06
    etadata
    -0.06
    ink
    -0.06
     pile
    -0.06
    POSITIVE LOGITS
     copying
    0.07
    们
    0.06
    ・ア
    0.06
     erfol
    0.06
    $MESS
    0.06
    incip
    0.06
     уровне
    0.06
     až
    0.06
     захоп
    0.06
     aggrav
    0.06
    Act Density 0.086%

    No Known Activations