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

    Neuronpedia

    INDEX
    Explanations

    duplicate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Air
    -0.07
     Handlers
    -0.06
     KERNEL
    -0.06
    inge
    -0.06
     Sky
    -0.06
    inas
    -0.06
     Berry
    -0.06
    369
    -0.06
    _heads
    -0.06
    Math
    -0.06
    POSITIVE LOGITS
     duplicate
    0.10
     Duplicate
    0.10
    _DU
    0.09
    Duplicate
    0.09
    _duplicate
    0.09
    Dup
    0.09
    duplicate
    0.08
     duplicated
    0.08
     dup
    0.08
    _duplicates
    0.08
    Act Density 0.005%

    No Known Activations