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

    Neuronpedia

    INDEX
    Explanations

    Guns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ونت
    -0.07
    struct
    -0.06
     connectors
    -0.06
     newborn
    -0.06
     reject
    -0.06
    _pattern
    -0.06
     ca
    -0.06
    licant
    -0.06
     fantas
    -0.06
    رت
    -0.06
    POSITIVE LOGITS
     Coral
    0.07
    ey
    0.07
    dashboard
    0.06
    semester
    0.06
     Thổ
    0.06
     kurul
    0.06
     داخل
    0.06
     застосування
    0.06
     tal
    0.06
    "For
    0.06
    Act Density 0.021%

    No Known Activations