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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    scroll
    -0.06
     �
    -0.06
    氏
    -0.06
     '<
    -0.06
     striving
    -0.06
    sei
    -0.06
    WIDTH
    -0.06
    Count
    -0.06
     син
    -0.06
    통
    -0.06
    POSITIVE LOGITS
     conclus
    0.07
    snd
    0.07
    (lua
    0.07
     najle
    0.06
     crackers
    0.06
     sanitize
    0.06
    (od
    0.06
    .pending
    0.06
    .are
    0.06
    0.06
    Act Density 0.031%

    No Known Activations