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

    Neuronpedia

    INDEX
    Explanations

    es

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WAL
    -0.07
     Bak
    -0.07
    -dot
    -0.07
     ож
    -0.06
    .material
    -0.06
     Hav
    -0.06
     उपलब
    -0.06
     thee
    -0.06
     �
    -0.06
    ilenames
    -0.06
    POSITIVE LOGITS
    347
    0.08
     suppress
    0.07
    .scala
    0.06
    邮箱
    0.06
    設
    0.06
     Marketplace
    0.06
    .play
    0.06
    Except
    0.06
     simplex
    0.06
    451
    0.06
    Act Density 0.001%

    No Known Activations