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

    Neuronpedia

    INDEX
    Explanations

    particular

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('/
    -0.07
    turnstile
    -0.07
     vurgu
    -0.06
    byte
    -0.06
     commande
    -0.06
    hits
    -0.06
    /proto
    -0.06
     eoqkrvldkf
    -0.06
    véd
    -0.06
    .communication
    -0.06
    POSITIVE LOGITS
     Purple
    0.07
     survivors
    0.06
     ASD
    0.06
     ulong
    0.06
    \User
    0.06
     Responses
    0.06
     glue
    0.06
    cene
    0.06
     advertisements
    0.06
     Riley
    0.06
    Act Density 0.002%

    No Known Activations