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

    Neuronpedia

    INDEX
    Explanations

    multiple choice questions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    툼
    -0.08
     أبريل
    -0.08
    .Student
    -0.07
     February
    -0.07
     Isaiah
    -0.07
     Serbian
    -0.07
    PerPage
    -0.07
    ,"%
    -0.07
    _mar
    -0.07
    وبة
    -0.07
    POSITIVE LOGITS
    轿
    0.08
    rank
    0.07
     activ
    0.07
     risky
    0.07
     trash
    0.07
     powering
    0.06
     runoff
    0.06
    built
    0.06
    百年
    0.06
    阿里
    0.06
    Act Density 0.022%

    No Known Activations