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

    Neuronpedia

    INDEX
    Explanations

    assistance and information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    opers
    -0.07
    ailer
    -0.06
    _corpus
    -0.06
    .Member
    -0.06
     daughters
    -0.06
    faq
    -0.06
    aeper
    -0.06
    _Login
    -0.06
    anja
    -0.06
    veillance
    -0.06
    POSITIVE LOGITS
    출장안마
    0.07
    	mesh
    0.07
     Tillerson
    0.06
    :_
    0.06
    	Z
    0.06
     wished
    0.06
    ًا
    0.06
     ทำ
    0.06
    升
    0.06
    CLE
    0.06
    Act Density 0.006%

    No Known Activations