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

    Neuronpedia

    INDEX
    Explanations

    letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ولی
    -0.07
     carousel
    -0.06
    Models
    -0.06
     увелич
    -0.06
    成本
    -0.06
    وني
    -0.06
     UAV
    -0.06
    اعب
    -0.06
     دارای
    -0.06
     installation
    -0.06
    POSITIVE LOGITS
     letters
    0.12
     Letter
    0.11
     letter
    0.11
     Letters
    0.11
     LETTER
    0.09
    Letters
    0.08
    -letter
    0.08
    panied
    0.08
     letterSpacing
    0.07
    Letter
    0.07
    Act Density 0.016%

    No Known Activations