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

    Neuronpedia

    INDEX
    Explanations

    Updates and announcements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .wav
    -0.07
     hlad
    -0.07
     bead
    -0.06
    .Zip
    -0.06
     solve
    -0.06
    .$
    -0.06
     하나
    -0.06
    费
    -0.06
    険
    -0.06
     itr
    -0.06
    POSITIVE LOGITS
    .space
    0.07
     وم
    0.07
     occupational
    0.07
    arseille
    0.07
    	Namespace
    0.06
    변
    0.06
     Stuttgart
    0.06
    TIM
    0.06
     Stoke
    0.06
     sophisticated
    0.06
    Act Density 0.128%

    No Known Activations