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

    Neuronpedia

    INDEX
    Explanations

    software development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     И
    -0.07
    greg
    -0.06
    ucher
    -0.06
     Var
    -0.06
     insignificant
    -0.06
     مر
    -0.06
     Amount
    -0.06
     ])
    -0.06
     curs
    -0.06
    .data
    -0.06
    POSITIVE LOGITS
    拼命
    0.08
     organizers
    0.07
    osome
    0.07
    (container
    0.07
     meisje
    0.07
     Gespräch
    0.07
     flying
    0.07
    train
    0.06
     confronted
    0.06
     les
    0.06
    Act Density 0.380%

    No Known Activations