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

    Neuronpedia

    INDEX
    Explanations

    brackets, parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    098
    -0.07
     qed
    -0.06
    PROTO
    -0.06
     �
    -0.06
    _decoder
    -0.06
     �
    -0.06
    .setup
    -0.06
    度
    -0.06
    _SPE
    -0.06
    maxLength
    -0.06
    POSITIVE LOGITS
     Koch
    0.07
    われ
    0.06
     begging
    0.06
     raids
    0.06
    onden
    0.06
     inspector
    0.06
     shots
    0.06
     ordinance
    0.06
    Rich
    0.06
    children
    0.06
    Act Density 0.007%

    No Known Activations