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

    Neuronpedia

    INDEX
    Explanations

    their

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Los
    -0.06
     tracked
    -0.06
     Boutique
    -0.06
    avana
    -0.06
    .Pass
    -0.06
     Fury
    -0.06
     نفت
    -0.06
    寶
    -0.06
     Psychology
    -0.06
     EntityType
    -0.05
    POSITIVE LOGITS
                               ↵
    0.07
    _rows
    0.07
    pecial
    0.06
    theses
    0.06
    /Data
    0.06
    .IsDBNull
    0.06
    employees
    0.06
     medication
    0.06
    /D
    0.06
    )){↵↵
    0.06
    Act Density 0.022%

    No Known Activations