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

    Neuronpedia

    INDEX
    Explanations

    envelope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incarn
    0.40
     Holm
    0.39
    㹂
    0.39
    ธาร
    0.38
     hors
    0.37
    ưng
    0.37
     जगत
    0.36
     रनों
    0.36
    噦
    0.36
    荿
    0.36
    POSITIVE LOGITS
     envelope
    4.13
     envelopes
    3.84
     Envelope
    3.84
    Envelope
    3.77
    envelope
    3.63
     envelop
    3.25
     envelopp
    3.03
     enveloped
    2.41
     enveloping
    2.31
     envol
    1.88
    Act Density 0.015%

    No Known Activations