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

    Neuronpedia

    INDEX
    Explanations

    questions and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     about
    -1.16
    AfterViewInit
    -1.09
    astify
    -1.06
    WithMany
    -1.00
    magitan
    -1.00
    িতে
    -0.98
    jetty
    -0.98
     in
    -0.97
     możemy
    -0.97
    lask
    -0.95
    POSITIVE LOGITS
    类似
    0.90
    ↵↵
    0.90
    著名的
    0.89
    Código
    0.89
    Zus
    0.88
    ستاگرام
    0.88
    そんな
    0.88
    頜
    0.87
    龙头
    0.86
     لأنه
    0.85
    Act Density 0.002%

    No Known Activations