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

    Neuronpedia

    INDEX
    Explanations

    debugging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Programs
    -0.06
     Universal
    -0.06
     trilogy
    -0.06
    .Private
    -0.06
    .centerX
    -0.06
    铁路
    -0.06
     عق
    -0.06
     Bhar
    -0.06
     Approach
    -0.06
     Directory
    -0.06
    POSITIVE LOGITS
    cgi
    0.07
     fraternity
    0.07
    ucks
    0.07
    mallow
    0.07
    باب
    0.06
    aramel
    0.06
    ómo
    0.06
    мати
    0.06
    solid
    0.06
    olith
    0.06
    Act Density 0.057%

    No Known Activations