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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     다시
    -0.07
     또
    -0.06
     �
    -0.06
     oath
    -0.06
     CNS
    -0.06
     Predicate
    -0.06
     DO
    -0.06
    _bind
    -0.06
    /no
    -0.06
     highlight
    -0.06
    POSITIVE LOGITS
     사건
    0.07
    ,
    0.07
     необ
    0.06
    まれ
    0.06
    MLElement
    0.06
     {|
    0.06
    ,len
    0.06
     :",
    0.06
    lique
    0.06
     lottery
    0.06
    Act Density 0.161%

    No Known Activations