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

    Neuronpedia

    INDEX
    Explanations

    narrative text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     briefed
    -0.07
     decad
    -0.07
     fanatic
    -0.07
     cultivated
    -0.07
    $('#
    -0.07
    OUNT
    -0.06
     опис
    -0.06
     id
    -0.06
     intermedi
    -0.06
     States
    -0.06
    POSITIVE LOGITS
     كه
    0.07
    كز
    0.07
    _|
    0.07
    كن
    0.06
    耶
    0.06
    itimate
    0.06
     võ
    0.06
    MAKE
    0.06
     Makeup
    0.06
    нання
    0.06
    Act Density 0.269%

    No Known Activations