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

    Neuronpedia

    INDEX
    Explanations

    Evil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Національ
    -0.07
    âce
    -0.07
    associ
    -0.07
    .signIn
    -0.07
    adays
    -0.06
    ��
    -0.06
     mars
    -0.06
    ADIUS
    -0.06
    enate
    -0.06
     Nowadays
    -0.06
    POSITIVE LOGITS
    -saving
    0.06
    ภาค
    0.06
    .“
    0.06
    یا
    0.06
     imaginable
    0.06
    Violation
    0.06
     tecr
    0.06
     electr
    0.06
     accom
    0.06
     furniture
    0.06
    Act Density 0.002%

    No Known Activations