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

    Neuronpedia

    INDEX
    Explanations

    Result

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (for
    -0.07
    .Mutex
    -0.06
    プ
    -0.06
    „To
    -0.06
    ACHINE
    -0.06
     stabilization
    -0.06
    aştır
    -0.06
    PO
    -0.06
    ops
    -0.06
     genome
    -0.06
    POSITIVE LOGITS
    Result
    0.07
     Remain
    0.07
     Result
    0.06
     Looking
    0.06
    .MESSAGE
    0.06
     NSStringFromClass
    0.06
     veloc
    0.06
    	plt
    0.06
    .Sockets
    0.06
    indsight
    0.06
    Act Density 0.002%

    No Known Activations