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

    Neuronpedia

    INDEX
    Explanations

    ://

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lawn
    -0.07
     divis
    -0.07
    acen
    -0.06
     rempl
    -0.06
     кал
    -0.06
     Hast
    -0.06
     ucfirst
    -0.06
    .school
    -0.06
    جات
    -0.06
    _SOL
    -0.06
    POSITIVE LOGITS
     minorities
    0.07
     outsiders
    0.06
     trimmed
    0.06
     XB
    0.06
     зм
    0.06
     civilizations
    0.06
    Ear
    0.06
    Environmental
    0.06
    igital
    0.06
     highway
    0.06
    Act Density 0.011%

    No Known Activations