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

    Neuronpedia

    INDEX
    Explanations

    Speaking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seven
    -0.07
    ex
    -0.07
     blow
    -0.07
     실제
    -0.06
    fix
    -0.06
     Forever
    -0.06
    71
    -0.06
     iterable
    -0.06
     Var
    -0.06
     Sleep
    -0.06
    POSITIVE LOGITS
    .”↵↵
    0.06
     poking
    0.06
    `↵↵
    0.06
     Unternehmen
    0.06
    ERRQ
    0.06
    dbh
    0.06
    วไป
    0.06
    >↵↵
    0.06
     Sas
    0.06
     Subaru
    0.06
    Act Density 0.058%

    No Known Activations