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

    Neuronpedia

    INDEX
    Explanations

    code structure and imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝐃
    -1.19
    iciaries
    -0.99
    WHEREAS
    -0.94
    ёр
    -0.92
    iciary
    -0.89
     NDEBUG
    -0.87
    richlet
    -0.85
    êng
    -0.84
     olympique
    -0.83
    //=
    -0.82
    POSITIVE LOGITS
     qualidade
    0.96
     definitivamente
    0.92
    といえば
    0.84
    gestaltung
    0.83
     brak
    0.82
     rudder
    0.82
    猝
    0.81
     dee
    0.81
     lorsque
    0.80
     températures
    0.80
    Act Density 0.161%

    No Known Activations