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

    Neuronpedia

    INDEX
    Explanations

    uncommon words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     Pey
    -0.06
     liegt
    -0.06
     strconv
    -0.06
    HTTPS
    -0.06
    onesia
    -0.06
     hears
    -0.06
     vhod
    -0.06
     upwards
    -0.06
    EndDate
    -0.06
    POSITIVE LOGITS
     evade
    0.07
     dentist
    0.07
    REL
    0.06
    ÜM
    0.06
     dysfunctional
    0.06
    Elite
    0.06
    �
    0.06
    .Proxy
    0.06
     застосування
    0.06
     нему
    0.05
    Act Density 0.000%

    No Known Activations