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

    Neuronpedia

    INDEX
    Explanations

    code statement terminator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чис
    0.46
    세대
    0.42
     autore
    0.42
     tensors
    0.42
    ниц
    0.40
    бро
    0.39
     universo
    0.39
     sociocultural
    0.38
     pek
    0.38
     vertebr
    0.38
    POSITIVE LOGITS
     ৫১
    0.40
     ৫
    0.38
    サイン
    0.38
     شويه
    0.37
     sobre
    0.37
    sobre
    0.37
    Sobre
    0.37
     விரைவில்
    0.36
     cinci
    0.36
     স্বীকৃতি
    0.36
    Act Density 0.002%

    No Known Activations