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

    Neuronpedia

    INDEX
    Explanations

    banking transactions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pkg
    -0.06
    ỗi
    -0.06
    ,M
    -0.06
     cosine
    -0.06
     erfolgreich
    -0.06
    ,char
    -0.06
     auc
    -0.06
    	number
    -0.06
     loyal
    -0.06
    เปล
    -0.06
    POSITIVE LOGITS
     Miscellaneous
    0.07
    JI
    0.07
     입니다
    0.07
     microwave
    0.07
    cbc
    0.06
    istics
    0.06
    aryana
    0.06
     حس
    0.06
    _helpers
    0.06
     الث
    0.06
    Act Density 0.004%

    No Known Activations