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

    Neuronpedia

    INDEX
    Explanations

    End of support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bene
    -0.08
     benefiting
    -0.07
     due
    -0.07
    𪾢
    -0.07
     individual
    -0.06
     Credit
    -0.06
    귿
    -0.06
     hunters
    -0.06
    富豪
    -0.06
    才能
    -0.06
    POSITIVE LOGITS
     الفور
    0.09
    嘘
    0.07
    STRING
    0.07
     ");
↵
    0.07
     новости
    0.07
    alerts
    0.07
    ％
    0.07
    ilee
    0.07
    metrical
    0.07
     새로
    0.07
    Act Density 0.031%

    No Known Activations