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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -angular
    -0.07
    (Return
    -0.06
    aphrag
    -0.06
     amour
    -0.06
    πλ
    -0.06
     Opport
    -0.06
     фор
    -0.06
     subsection
    -0.06
    382
    -0.06
    διά
    -0.06
    POSITIVE LOGITS
     Beckham
    0.10
    calc
    0.10
    吗
    0.07
    頼
    0.07
    SH
    0.07
    �
    0.07
    ^-
    0.06
     شهر
    0.06
     Calls
    0.06
    ='')
    0.06
    Act Density 0.002%

    No Known Activations