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

    Neuronpedia

    INDEX
    Explanations

    mathematical proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .FloatField
    -0.07
    .EditorButton
    -0.06
    redentials
    -0.06
     customerId
    -0.06
    モ
    -0.06
    ynes
    -0.06
    .Entry
    -0.06
    907
    -0.06
    fgets
    -0.06
     民
    -0.06
    POSITIVE LOGITS
     dům
    0.07
    ира
    0.06
    CUR
    0.06
     rej
    0.06
     Rhodes
    0.06
     Oscar
    0.06
    desired
    0.06
     Personally
    0.06
    ває
    0.06
     Sapphire
    0.06
    Act Density 0.063%

    No Known Activations