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

    Neuronpedia

    INDEX
    Explanations

    HTTP headers and backend routes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ミネ
    0.41
     Whis
    0.40
     ju
    0.39
    Whis
    0.38
    TGFuZ
    0.38
     Patt
    0.36
     Pluto
    0.36
    ல
    0.36
     sandalwood
    0.36
    ድ
    0.36
    POSITIVE LOGITS
    ("@
    0.46
     健康
    0.44
    健康的
    0.44
    健康
    0.42
    LogProfile
    0.41
     header
    0.41
     HEALTH
    0.40
     swim
    0.39
     backend
    0.39
     /**@
    0.39
    Act Density 0.007%

    No Known Activations