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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dm
    -0.08
    Donate
    -0.07
     killer
    -0.07
    타이
    -0.06
     TE
    -0.06
     Layer
    -0.06
    loss
    -0.06
    .sym
    -0.06
     potency
    -0.06
    667
    -0.06
    POSITIVE LOGITS
    ará
    0.07
     aVar
    0.07
    	api
    0.07
    .Type
    0.07
    .Mongo
    0.07
     such
    0.07
     คาส
    0.07
    'b
    0.06
    	close
    0.06
    _MATRIX
    0.06
    Act Density 0.001%

    No Known Activations