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

    Neuronpedia

    INDEX
    Explanations

    viruses and proteins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jewe
    -0.09
     Emily
    -0.08
     اتباع
    -0.08
    wass
    -0.07
     gesammelt
    -0.07
     Discovery
    -0.07
     schön
    -0.07
    -0.07
     vider
    -0.07
     shareholder
    -0.07
    POSITIVE LOGITS
     horeca
    0.09
     $.
    0.08
    $.
    0.08
    €.
    0.08
    .qt
    0.08
     produit
    0.08
    .sections
    0.08
     kontinu
    0.07
     inherent
    0.07
     adaptability
    0.07
    Act Density 0.003%

    No Known Activations