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

    Neuronpedia

    INDEX
    Explanations

    say "ur" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    얀
    -0.07
    .vec
    -0.07
    ac
    -0.07
    .Resize
    -0.07
     cải
    -0.07
    棒
    -0.06
    ผลกระท
    -0.06
     referred
    -0.06
     doesn
    -0.06
     וכך
    -0.06
    POSITIVE LOGITS
    >equals
    0.08
     CRM
    0.07
    YW
    0.07
    Manage
    0.07
    John
    0.07
    <>(
    0.07
    😯
    0.07
    irror
    0.07
    BASH
    0.07
    shares
    0.07
    Act Density 0.002%

    No Known Activations