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

    Neuronpedia

    INDEX
    Explanations

    research papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Representation
    -0.07
    getSize
    -0.07
     std
    -0.06
     Lauren
    -0.06
     thấp
    -0.06
    (New
    -0.06
    _identifier
    -0.06
     Thai
    -0.06
    Converted
    -0.06
    umbnails
    -0.06
    POSITIVE LOGITS
    likleri
    0.07
    ğini
    0.06
     vej
    0.06
    ubre
    0.06
     indulge
    0.06
     figura
    0.06
     BUY
    0.06
    indre
    0.06
    ไข
    0.06
    _Position
    0.06
    Act Density 0.198%

    No Known Activations