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

    Neuronpedia

    INDEX
    Explanations

    Max

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CA
    -0.07
    %">
    -0.06
     Cult
    -0.06
     cre
    -0.06
    طان
    -0.06
     rally
    -0.06
     diffé
    -0.06
    �
    -0.06
    �
    -0.06
    ыш
    -0.06
    POSITIVE LOGITS
     Marlins
    0.07
     бути
    0.07
    \Tests
    0.06
    煤
    0.06
     малень
    0.06
    lock
    0.06
     blooms
    0.06
    .Large
    0.06
     به
    0.06
    _REAL
    0.06
    Act Density 0.001%

    No Known Activations