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

    Neuronpedia

    INDEX
    Explanations

    Certificates and encoding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ycop
    -0.07
    保护
    -0.07
    alen
    -0.07
    سی
    -0.06
     matchup
    -0.06
    सन
    -0.06
    키
    -0.06
    ibility
    -0.06
    ients
    -0.06
    алов
    -0.06
    POSITIVE LOGITS
    -del
    0.07
    陶
    0.06
    _av
    0.06
     이용
    0.06
    eil
    0.06
    �
    0.06
     tái
    0.06
    (++
    0.06
     kvůli
    0.06
     Cert
    0.06
    Act Density 0.015%

    No Known Activations