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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dign
    -0.06
     fest
    -0.06
    ์พ
    -0.06
     мі
    -0.06
    átní
    -0.06
     モ
    -0.06
    -p
    -0.06
     Гри
    -0.06
     PRE
    -0.06
     서버
    -0.06
    POSITIVE LOGITS
     caught
    0.07
    Repair
    0.06
    _ds
    0.06
     созд
    0.06
    _proj
    0.06
     Cory
    0.06
     Repair
    0.06
    션
    0.06
    nx
    0.06
     Lana
    0.06
    Act Density 0.000%

    No Known Activations