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

    Neuronpedia

    INDEX
    Explanations

    commons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     storage
    -0.06
    meg
    -0.06
    Dice
    -0.06
    Select
    -0.06
     co
    -0.06
    Enough
    -0.06
     detecting
    -0.06
     reform
    -0.06
    ursion
    -0.06
    ndef
    -0.06
    POSITIVE LOGITS
     interconnected
    0.06
     reasoned
    0.06
    _AS
    0.06
    ließ
    0.06
    IntervalSince
    0.06
     localVar
    0.06
     closet
    0.06
    lx
    0.06
    чивается
    0.06
     McCart
    0.06
    Act Density 0.000%

    No Known Activations