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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASCADE
    -0.06
    GLISH
    -0.06
    Comput
    -0.06
    esus
    -0.06
    ież
    -0.06
     Bulld
    -0.06
     Austr
    -0.06
    tribution
    -0.06
     Decision
    -0.06
    cete
    -0.06
    POSITIVE LOGITS
     errs
    0.07
    ...(
    0.06
    illegal
    0.06
    -account
    0.06
    (ins
    0.06
     giống
    0.06
    ِم
    0.06
     Metallic
    0.06
    ,,
    0.06
     flakes
    0.06
    Act Density 0.000%

    No Known Activations