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

    Neuronpedia

    INDEX
    Explanations

    periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nonexistent
    -0.09
     trash
    -0.07
     fluct
    -0.07
     efficiency
    -0.07
     cruiser
    -0.07
     efficiënt
    -0.07
     evaporation
    -0.07
     entscheid
    -0.07
     रिकॉर्ड
    -0.07
     तरी
    -0.07
    POSITIVE LOGITS
     ayrıca
    0.08
    dessen
    0.08
    敬
    0.08
    ando
    0.08
    iraz
    0.08
    Daarnaast
    0.08
    ylch
    0.08
    gia
    0.07
    hau
    0.07
    ukela
    0.07
    Act Density 0.017%

    No Known Activations