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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }.
    -0.07
    举例
    -0.07
    bers
    -0.07
     factor
    -0.07
    ….
    -0.07
    dsa
    -0.07
    எ
    -0.07
    fold
    -0.07
    دو
    -0.07
    لل
    -0.07
    POSITIVE LOGITS
     Artem
    0.09
     stagn
    0.07
    pii
    0.07
    蓊
    0.07
    �
    0.07
    Ret
    0.07
    相对较
    0.07
     Cycl
    0.07
     decryption
    0.07
     postpon
    0.07
    Act Density 0.011%

    No Known Activations