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

    Neuronpedia

    INDEX
    Explanations

    lists codes numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.06
     Bram
    -0.06
     спе
    -0.06
    :".$
    -0.06
    -level
    -0.06
     Angus
    -0.06
    そ
    -0.06
     alleges
    -0.06
    .codec
    -0.05
     Chow
    -0.05
    POSITIVE LOGITS
     독일
    0.07
    .
↵
    0.07
    tiny
    0.06
     thieves
    0.06
    üy
    0.06
    Girls
    0.06
    ZW
    0.06
    _creator
    0.06
    /value
    0.06
    ě
    0.06
    Act Density 0.000%

    No Known Activations