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

    Neuronpedia

    INDEX
    Explanations

    friendship and commitment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    datast
    0.40
     وار
    0.39
    아가
    0.38
    LI
    0.36
    gpio
    0.36
     alemão
    0.36
     desempenho
    0.35
    clusión
    0.35
    dat
    0.35
    нів
    0.35
    POSITIVE LOGITS
    譜
    0.40
     Kingdoms
    0.39
     PATH
    0.38
    uruh
    0.38
    噻
    0.37
     plummeted
    0.36
    ərə
    0.36
    辄
    0.35
     rumored
    0.35
    مارات
    0.35
    Act Density 0.000%

    No Known Activations