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

    Neuronpedia

    INDEX
    Explanations

    Academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ảng
    -0.06
    ,Q
    -0.06
     Cz
    -0.06
    □□
    -0.06
    の人
    -0.06
    _WS
    -0.06
     spree
    -0.06
    "."
    -0.06
    -z
    -0.06
    Avoid
    -0.06
    POSITIVE LOGITS
    說
    0.07
    rebbe
    0.07
    ری
    0.07
    ेप
    0.06
    یست
    0.06
     consume
    0.06
    说
    0.06
     Natural
    0.06
     SSA
    0.06
     Necklace
    0.06
    Act Density 0.005%

    No Known Activations