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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .loadtxt
    -0.07
    +"\
    -0.07
     jedná
    -0.07
    ουν
    -0.07
    τικα
    -0.07
    рех
    -0.06
    ixin
    -0.06
    INCLUDE
    -0.06
    ニ
    -0.06
    기타
    -0.06
    POSITIVE LOGITS
    (Int
    0.06
                    ↵                ↵
    0.06
    MAIL
    0.06
    's
    0.06
    acija
    0.06
    (proto
    0.06
    udiant
    0.06
    'email
    0.06
    �
    0.05
    ؟↵
    0.05
    Act Density 0.004%

    No Known Activations