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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chất
    -0.08
    Э
    -0.07
    Cliente
    -0.07
    Usuario
    -0.07
     Inserts
    -0.07
     sharedApplication
    -0.07
    (URL
    -0.07
    prepared
    -0.07
    \Session
    -0.07
    补充
    -0.07
    POSITIVE LOGITS
    —or
    0.08
    Nat
    0.08
    ************************************************************************
    0.07
     Nat
    0.07
    Kat
    0.07
    hof
    0.07
    老头
    0.06
     hen
    0.06
     де
    0.06
    ;z
    0.06
    Act Density 0.008%

    No Known Activations