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

    Neuronpedia

    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cable
    -0.08
     Soldiers
    -0.08
     soldiers
    -0.08
    :\"
    -0.08
     ihn
    -0.08
    friends
    -0.08
    či
    -0.08
     Traders
    -0.07
     вооруж
    -0.07
    ژه
    -0.07
    POSITIVE LOGITS
     message
    0.08
    (_,
    0.08
    Cannot
    0.07
    (message
    0.07
    Admin
    0.07
     migration
    0.07
    Mutable
    0.07
    message
    0.07
    Preset
    0.07
    Encoder
    0.07
    Act Density 0.002%

    No Known Activations