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

    Neuronpedia

    INDEX
    Explanations

    @param documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funk
    0.43
    高的
    0.42
    Funk
    0.41
     Johann
    0.39
     Huan
    0.39
    ادس
    0.39
     Funk
    0.39
     sadd
    0.38
    明顯
    0.38
     indign
    0.38
    POSITIVE LOGITS
    access
    0.51
    link
    0.50
     acesso
    0.49
     access
    0.47
    package
    0.47
     доступа
    0.47
     acess
    0.46
    covers
    0.46
    bool
    0.44
    Acces
    0.44
    Act Density 0.001%

    No Known Activations