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

    Neuronpedia

    INDEX
    Explanations

    ingredients and components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Crime
    -0.08
     Permissions
    -0.07
    ทอง
    -0.07
     Between
    -0.06
     Species
    -0.06
     QUESTION
    -0.06
    School
    -0.06
    结合
    -0.06
    Psy
    -0.06
     бактер
    -0.06
    POSITIVE LOGITS
     restarting
    0.06
    translate
    0.06
    *M
    0.06
     Sophia
    0.06
     러
    0.06
     Gover
    0.06
     تلف
    0.06
     skating
    0.06
     presets
    0.06
    APH
    0.06
    Act Density 0.161%

    No Known Activations