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

    Neuronpedia

    INDEX
    Explanations

    asylum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     march
    -0.07
     forge
    -0.06
    pcf
    -0.06
     würde
    -0.06
     belt
    -0.06
     Sakura
    -0.06
    icontrol
    -0.06
     Debbie
    -0.06
     technik
    -0.06
    ////////////////////////////////////////////////
    -0.06
    POSITIVE LOGITS
     asylum
    0.08
    ToSelector
    0.06
     담
    0.06
     STRUCT
    0.06
    _encoder
    0.06
     Honey
    0.06
    Systems
    0.06
    ーレ
    0.06
     기능
    0.06
    _ASSERT
    0.06
    Act Density 0.001%

    No Known Activations