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

    Neuronpedia

    INDEX
    Explanations

    legal/financial contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adan
    -0.07
    '])){↵
    -0.07
    ala
    -0.06
    	usage
    -0.06
    classNames
    -0.06
     kaydet
    -0.06
    уже
    -0.06
    ()))
↵
    -0.06
     王
    -0.06
     enr
    -0.06
    POSITIVE LOGITS
    OLER
    0.07
     bounty
    0.07
     frost
    0.06
     worthy
    0.06
     Advertising
    0.06
    redict
    0.06
    ۱۰
    0.06
    极
    0.06
     predicting
    0.06
     Нав
    0.06
    Act Density 0.011%

    No Known Activations