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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     effectively
    -0.07
     dto
    -0.07
     power
    -0.06
     dumped
    -0.06
    -drop
    -0.06
    wealth
    -0.06
    trak
    -0.06
    Alignment
    -0.06
     spelling
    -0.06
     venue
    -0.06
    POSITIVE LOGITS
    овари
    0.08
     Bas
    0.07
     ÜNİ
    0.07
    으
    0.07
    markers
    0.07
    님의
    0.07
    .Calendar
    0.07
     Als
    0.06
     Aer
    0.06
     Aqu
    0.06
    Act Density 0.010%

    No Known Activations