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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trả
    -0.07
    Ě
    -0.07
     پشت
    -0.07
     ΠΑΝ
    -0.06
     unlikely
    -0.06
    大阪
    -0.06
    िण
    -0.06
     ठ
    -0.06
     opatření
    -0.06
     布
    -0.06
    POSITIVE LOGITS
    entered
    0.07
     Lights
    0.07
    %m
    0.07
    _xyz
    0.06
     namely
    0.06
    .layers
    0.06
     cleric
    0.06
    /in
    0.06
    ButtonTitles
    0.06
    };↵↵
    0.06
    Act Density 0.000%

    No Known Activations