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

    Neuronpedia

    INDEX
    Explanations

    communist manifesto, computation, began, vulkan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Tull
    0.92
     MTS
    0.91
     Mock
    0.90
     Bloom
    0.90
     Mon
    0.85
     multichannel
    0.84
     Kall
    0.83
     mins
    0.82
     MB
    0.82
     Lara
    0.82
    POSITIVE LOGITS
     we
    2.32
    we
    2.10
    We
    1.98
     We
    1.92
    我们
    1.82
    เรา
    1.81
    我們
    1.77
     kita
    1.74
    私たちは
    1.67
     我们
    1.65
    Act Density 0.109%

    No Known Activations