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

    Neuronpedia

    INDEX
    Explanations

    Naval military terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ．．．
    -0.83
    diğim
    -0.83
     系
    -0.76
    魔女
    -0.75
    ^=
    -0.75
    шению
    -0.75
    浜
    -0.75
    ⑤
    -0.71
     rios
    -0.71
    ocidad
    -0.71
    POSITIVE LOGITS
     architects
    0.98
     avi
    0.91
    ny
    0.89
    anned
    0.86
     warfare
    0.86
    ional
    0.81
    few
    0.81
     pim
    0.79
     forces
    0.79
    melen
    0.78
    Act Density 0.029%

    No Known Activations