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

    Neuronpedia

    INDEX
    Explanations

    teammates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ng
    -0.07
     criminals
    -0.06
     FIR
    -0.06
     resort
    -0.06
     bảng
    -0.06
    sar
    -0.06
    �
    -0.06
    ',[
    -0.06
     towels
    -0.06
    /,
    -0.06
    POSITIVE LOGITS
     teammates
    0.31
     teammate
    0.28
     vnitř
    0.07
    ілі
    0.07
     vyh
    0.07
     учит
    0.07
     політи
    0.07
    üstü
    0.07
     восп
    0.06
    yyyy
    0.06
    Act Density 0.001%

    No Known Activations