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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wik
    -0.07
    &o
    -0.07
     Carolina
    -0.07
    iros
    -0.06
     aj
    -0.06
     Defence
    -0.06
     Oregon
    -0.06
    criptor
    -0.06
    �
    -0.06
     Andres
    -0.06
    POSITIVE LOGITS
     $("#"
    0.06
     Sauce
    0.06
    (number
    0.06
     muscle
    0.06
     expert
    0.06
    .CreateTable
    0.06
    (confirm
    0.06
     sauce
    0.06
     metavar
    0.06
     convictions
    0.06
    Act Density 0.045%

    No Known Activations