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

    Neuronpedia

    INDEX
    Explanations

    Questions and how-to instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clan
    -0.07
    �
    -0.06
     stepped
    -0.06
     practice
    -0.06
     Masters
    -0.06
    ег
    -0.06
     autonomous
    -0.06
    IGNAL
    -0.06
     thiên
    -0.06
     patrons
    -0.06
    POSITIVE LOGITS
    /disable
    0.08
     kolay
    0.08
    _similarity
    0.07
    !!!↵↵
    0.07
     /*<<<
    0.07
     husus
    0.07
    uckland
    0.07
    .Cross
    0.07
    /member
    0.06
    ीकरण
    0.06
    Act Density 0.011%

    No Known Activations