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

    Neuronpedia

    INDEX
    Explanations

    pump

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Texture
    -0.07
     Chrom
    -0.07
    _encode
    -0.07
    ekk
    -0.07
     웨
    -0.06
     metavar
    -0.06
    ohen
    -0.06
    .Fire
    -0.06
     صح
    -0.06
    ullen
    -0.06
    POSITIVE LOGITS
    ，你
    0.07
    antages
    0.06
     amendments
    0.06
     कथ
    0.06
     pump
    0.06
    .“
    0.06
    aklı
    0.06
     says
    0.06
     prevail
    0.06
    macı
    0.06
    Act Density 0.001%

    No Known Activations