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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brother
    -0.07
    �
    -0.07
    cases
    -0.06
    ником
    -0.06
     seeding
    -0.06
     уник
    -0.06
    _dist
    -0.06
     cycle
    -0.06
    従
    -0.06
    cycle
    -0.06
    POSITIVE LOGITS
     spa
    0.17
     Spa
    0.14
     spas
    0.11
    spa
    0.09
    SPA
    0.08
     uğra
    0.08
     SPA
    0.07
    Sep
    0.07
     Gala
    0.07
    Company
    0.07
    Act Density 0.003%

    No Known Activations