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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    есс
    -0.07
    اء
    -0.07
    DESC
    -0.07
    해
    -0.06
    -Free
    -0.06
     Covers
    -0.06
    _fake
    -0.06
    UserService
    -0.06
    自由
    -0.06
     GAS
    -0.06
    POSITIVE LOGITS
    Stored
    0.07
    ased
    0.07
     photograph
    0.06
     whatever
    0.06
    ezpe
    0.06
     Melbourne
    0.06
     〉
    0.06
     polluted
    0.06
     deduct
    0.06
    meld
    0.06
    Act Density 0.038%

    No Known Activations