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

    Neuronpedia

    INDEX
    Explanations

    programming libraries and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    พร
    -0.07
     arrog
    -0.07
    /sc
    -0.07
     prohibition
    -0.06
     δο
    -0.06
     SEG
    -0.06
     forged
    -0.06
     inspectors
    -0.06
    -fix
    -0.06
     Stoke
    -0.06
    POSITIVE LOGITS
     kamu
    0.07
     Arthropoda
    0.06
     台
    0.06
     свидетель
    0.06
     }}>↵
    0.06
    269
    0.06
    े.
    0.06
     Počet
    0.06
    ><![
    0.06
    !',
    0.06
    Act Density 0.000%

    No Known Activations