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

    Neuronpedia

    INDEX
    Explanations

    death/negative news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    trail
    -0.06
     development
    -0.06
    onclick
    -0.06
    لف
    -0.06
    /menu
    -0.06
     hdc
    -0.06
     Brend
    -0.06
    )#
    -0.06
     flats
    -0.06
    altitude
    -0.06
    POSITIVE LOGITS
     Hawai
    0.07
     Salmon
    0.07
    .AddListener
    0.06
     Nullable
    0.06
     dém
    0.06
     Prism
    0.06
     Bull
    0.06
    ughter
    0.06
    TURE
    0.06
     stationed
    0.06
    Act Density 0.069%

    No Known Activations