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

    Neuronpedia

    INDEX
    Explanations

    Code and state abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ashion
    -0.08
    estival
    -0.08
     F
    -0.08
    ORD
    -0.08
    usion
    -0.08
    leet
    -0.08
    RESH
    -0.08
    IRM
    -0.07
    LOOR
    -0.07
    ERENCE
    -0.07
    POSITIVE LOGITS
    assertFalse
    0.06
    _installed
    0.06
    FU
    0.06
    fib
    0.06
     Ned
    0.06
    .CREATED
    0.06
    hevik
    0.06
    812
    0.06
     unmarried
    0.06
    FTA
    0.06
    Act Density 0.071%

    No Known Activations