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

    Neuronpedia

    INDEX
    Explanations

    recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nación
    0.40
    管
    0.38
    ukin
    0.37
    во
    0.37
     суть
    0.37
    enta
    0.36
     levando
    0.36
    verband
    0.35
     PEN
    0.35
     organiz
    0.35
    POSITIVE LOGITS
     architectures
    0.49
    something
    0.45
    Something
    0.42
     something
    0.42
    architecture
    0.41
    ാന
    0.39
    ရှိ
    0.39
    There
    0.38
    اله
    0.38
     Theoretically
    0.38
    Act Density 0.002%

    No Known Activations