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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocrates
    -0.07
     produto
    -0.07
     HMS
    -0.07
     BSD
    -0.07
     tüm
    -0.06
     CRUD
    -0.06
    Б
    -0.06
     Rows
    -0.06
     OSI
    -0.06
     breeds
    -0.06
    POSITIVE LOGITS
    Fatal
    0.07
    另一
    0.07
    도가
    0.07
     A
    0.07
     anger
    0.07
    كن
    0.06
    getDoctrine
    0.06
     adore
    0.06
    了一
    0.06
    $l
    0.06
    Act Density 0.008%

    No Known Activations