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

    Neuronpedia

    INDEX
    Explanations

    bank

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =================================
    -0.07
     Conservatives
    -0.07
    alpha
    -0.06
    blocked
    -0.06
     insects
    -0.06
    474
    -0.06
    trinsic
    -0.06
     dozen
    -0.06
    企業
    -0.06
    .fm
    -0.06
    POSITIVE LOGITS
    ','"+
    0.07
     nedok
    0.07
     :.|
    0.07
     shootout
    0.06
    (Audio
    0.06
    ","",
    0.06
     أل
    0.06
     Putin
    0.06
     Poker
    0.06
    .labels
    0.06
    Act Density 0.360%

    No Known Activations