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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Это
    -0.08
    }};↵
    -0.07
     hran
    -0.07
    ертв
    -0.06
     algebra
    -0.06
    ]])↵↵
    -0.06
     Songs
    -0.06
     />);↵
    -0.06
    step
    -0.06
     ));↵↵
    -0.06
    POSITIVE LOGITS
     FileName
    0.07
    ,GL
    0.07
     корол
    0.07
    endency
    0.07
    .ent
    0.07
     Araştır
    0.07
     meantime
    0.06
     Yatırım
    0.06
    км
    0.06
    udit
    0.06
    Act Density 0.000%

    No Known Activations