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

    Neuronpedia

    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ?><?
    -0.06
    /pub
    -0.06
     لذا
    -0.06
    ूस
    -0.06
     مطرح
    -0.06
    culate
    -0.06
     بما
    -0.06
    evenodd
    -0.06
     kari
    -0.06
    财
    -0.06
    POSITIVE LOGITS
     filtr
    0.08
    ipel
    0.07
     manager
    0.07
     Daughter
    0.07
    (compare
    0.07
    èle
    0.06
    .SQL
    0.06
     convenience
    0.06
     });↵↵↵
    0.06
     reliability
    0.06
    Act Density 0.045%

    No Known Activations