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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Το
    -0.07
    	initial
    -0.07
     Lebens
    -0.07
     Mech
    -0.07
     chilly
    -0.06
     deactivated
    -0.06
    icap
    -0.06
     dados
    -0.06
     gigantic
    -0.06
     yelled
    -0.06
    POSITIVE LOGITS
    _AUT
    0.07
     brat
    0.06
    -char
    0.06
     Poe
    0.06
     scri
    0.06
     BOOL
    0.06
     сос
    0.06
     reminded
    0.06
    Browsable
    0.05
     Prev
    0.05
    Act Density 0.249%

    No Known Activations