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

    Neuronpedia

    INDEX
    Explanations

    thread

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Merge
    -0.07
     Analyzer
    -0.07
     nearing
    -0.07
     poisoning
    -0.07
     analy
    -0.07
    .Merge
    -0.07
    clients
    -0.06
    (r
    -0.06
    (routes
    -0.06
     editor
    -0.06
    POSITIVE LOGITS
    τι
    0.06
    發
    0.06
     어�
    0.06
     الل
    0.06
    iated
    0.06
     اتحاد
    0.06
     espec
    0.06
    dur
    0.06
     grup
    0.06
     مطال
    0.06
    Act Density 0.005%

    No Known Activations