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

    Neuronpedia

    INDEX
    Explanations

    Authorization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nt
    -0.08
    _converter
    -0.07
     indigenous
    -0.07
     deer
    -0.07
     taxi
    -0.07
     JB
    -0.07
     meg
    -0.07
    rng
    -0.07
     edx
    -0.07
     orc
    -0.07
    POSITIVE LOGITS
    UserData
    0.08
    りました
    0.07
    By
    0.07
    しました
    0.07
     substit
    0.07
    =".$
    0.07
     userEmail
    0.06
    "]."
    0.06
     רו
    0.06
    .sendMessage
    0.06
    Act Density 0.003%

    No Known Activations