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

    Neuronpedia

    INDEX
    Explanations

    offering to try another

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     keg
    0.45
     debemos
    0.40
     poprzez
    0.39
     zg
    0.39
     tourist
    0.39
     있고
    0.39
     containment
    0.39
     doit
    0.39
     벽
    0.39
     ಪ್ರಾರಂಭ
    0.39
    POSITIVE LOGITS
    लाक
    0.46
     विशेषज्ञ
    0.41
    Knife
    0.40
    Oxford
    0.38
    UKI
    0.37
    日志
    0.37
    ronics
    0.37
    JACK
    0.37
    Vorlage
    0.37
    жений
    0.36
    Act Density 0.000%

    No Known Activations