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
     Contract
    -0.06
    кового
    -0.06
    kor
    -0.06
    anzi
    -0.06
    455
    -0.06
    Past
    -0.06
     overhead
    -0.06
    })(
    -0.06
    )r
    -0.06
    fout
    -0.06
    POSITIVE LOGITS
     다음과
    0.08
    (inode
    0.07
    araoh
    0.07
    :length
    0.06
    (inp
    0.06
     ([]
    0.06
    _phase
    0.06
    股份有限公司
    0.06
    807
    0.06
    paněl
    0.06
    Act Density 0.001%

    No Known Activations