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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Dre
    -0.07
    \'
    -0.06
     staying
    -0.06
    <Boolean
    -0.06
    kou
    -0.06
     famously
    -0.06
     potentially
    -0.06
     노출등록
    -0.06
     markedly
    -0.06
     roast
    -0.06
    POSITIVE LOGITS
     liter
    0.06
     print
    0.06
     갑
    0.06
    ิทธ
    0.06
     adresse
    0.06
     �
    0.06
    .']
    0.06
    .Global
    0.06
    .:.:.:.
    0.06
    REL
    0.06
    Act Density 0.002%

    No Known Activations