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

    Neuronpedia

    INDEX
    Explanations

    measured in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    горь
    0.46
    協
    0.45
    मला
    0.44
     atractivo
    0.44
    掏
    0.43
    𝓽
    0.42
     essentiel
    0.42
    اني
    0.41
    飲
    0.41
    var
    0.41
    POSITIVE LOGITS
    kV
    0.48
     필
    0.46
    Ệ
    0.46
     moths
    0.46
     bus
    0.44
    КИ
    0.44
     Service
    0.43
     Nazis
    0.43
     উপায়
    0.43
    UTRAL
    0.43
    Act Density 0.001%

    No Known Activations