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

    Neuronpedia

    INDEX
    Explanations

    Graphs and networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mai
    -0.07
    نین
    -0.06
    _TH
    -0.06
     Programm
    -0.06
    xdd
    -0.06
     Exit
    -0.06
     accompany
    -0.06
    _yaw
    -0.06
    ombat
    -0.06
    スポ
    -0.06
    POSITIVE LOGITS
    ><![
    0.06
    	want
    0.06
    childNodes
    0.06
    _filters
    0.06
     Wheeler
    0.06
     offseason
    0.06
     tossing
    0.05
     Assertions
    0.05
    Andrew
    0.05
     ylabel
    0.05
    Act Density 0.015%

    No Known Activations