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

    Neuronpedia

    INDEX
    Explanations

    irmware

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Celtic
    -0.07
    화를
    -0.07
     lip
    -0.06
    /testify
    -0.06
    разд
    -0.06
     Freund
    -0.06
    ️
    -0.06
     kaydet
    -0.06
    erd
    -0.06
    POSITIVE LOGITS
    touches
    0.06
    )<
    0.06
    sigmoid
    0.06
     shaders
    0.06
     embodied
    0.06
     vertices
    0.06
     Johannesburg
    0.06
     radiant
    0.06
    	sock
    0.06
    сер
    0.06
    Act Density 0.018%

    No Known Activations