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

    Neuronpedia

    INDEX
    Explanations

    Reynolds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     agradável
    -0.09
    כן
    -0.09
     али
    -0.08
     devastated
    -0.08
    (exports
    -0.08
     cheval
    -0.08
    __(*
    -0.08
    /helpers
    -0.08
     difficulté
    -0.08
     functioneren
    -0.08
    POSITIVE LOGITS
     Picker
    0.08
     forwarding
    0.07
     Stuart
    0.07
    xxx
    0.07
     permitting
    0.07
     xxx
    0.07
    omite
    0.07
     John
    0.07
     VS
    0.07
     flirting
    0.07
    Act Density 0.001%

    No Known Activations