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

    Neuronpedia

    INDEX
    Explanations

    Time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ारक
    -0.07
     Utah
    -0.07
    Delay
    -0.07
     flowed
    -0.07
    prototype
    -0.07
    ιώ
    -0.06
     Loan
    -0.06
     Motion
    -0.06
     allocate
    -0.06
     Coral
    -0.06
    POSITIVE LOGITS
     �
    0.07
     StringUtil
    0.06
     ді
    0.06
     cgi
    0.06
     kaç
    0.06
    τζ
    0.06
    (TokenType
    0.06
    нє
    0.06
     Cách
    0.06
    ประโยชน
    0.06
    Act Density 0.026%

    No Known Activations