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

    Neuronpedia

    INDEX
    Explanations

    counts as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ोक
    -0.07
     coating
    -0.07
     up
    -0.06
    数学
    -0.06
    (test
    -0.06
    	Command
    -0.06
    }.${
    -0.06
     Host
    -0.06
    lineno
    -0.06
     day
    -0.06
    POSITIVE LOGITS
    Photo
    0.06
     Towards
    0.06
     Techn
    0.06
     drž
    0.06
    自治
    0.06
     multiplied
    0.06
     FactoryGirl
    0.06
    Fant
    0.06
     harmon
    0.06
    inst
    0.06
    Act Density 0.025%

    No Known Activations