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

    Neuronpedia

    INDEX
    Explanations

    Russian

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    神秘
    -0.07
     glean
    -0.07
    アメリカ
    -0.07
    põ
    -0.07
    tures
    -0.07
    ampton
    -0.07
    乏力
    -0.07
     Cameron
    -0.07
     imprison
    -0.07
    (Class
    -0.06
    POSITIVE LOGITS
    ’S
    0.07
    }),
    0.07
    Negative
    0.07
    >("
    0.06
    .Maybe
    0.06
    -devel
    0.06
     Benef
    0.06
    专访
    0.06
    VES
    0.06
    PAY
    0.06
    Act Density 0.001%

    No Known Activations