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

    Neuronpedia

    INDEX
    Explanations

    Possibility/Impossibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("(%
    -0.06
    .enumer
    -0.06
    (download
    -0.06
     rough
    -0.06
     HC
    -0.06
    /column
    -0.06
    woods
    -0.06
    	swap
    -0.06
     servants
    -0.06
    lland
    -0.06
    POSITIVE LOGITS
     contin
    0.06
    itates
    0.06
     фот
    0.06
     뉴
    0.06
    表示
    0.06
    ENC
    0.06
     entail
    0.06
     клас
    0.06
     cré
    0.06
    ////////////////////////////////////////////////////
    0.06
    Act Density 0.041%

    No Known Activations