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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adet
    -0.07
     crusher
    -0.07
     understandably
    -0.07
    Pager
    -0.06
     Bölüm
    -0.06
     metre
    -0.06
     designers
    -0.06
    kart
    -0.06
    เสนอ
    -0.06
     didnt
    -0.06
    POSITIVE LOGITS
     कह
    0.06
    围
    0.06
    ΄
    0.06
    ?>:</
    0.06
    ghan
    0.06
    ,)
    0.05
    .OneToOne
    0.05
    (Server
    0.05
     aff
    0.05
    .visualization
    0.05
    Act Density 0.013%

    No Known Activations