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

    Neuronpedia

    INDEX
    Explanations

    returning home

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     çık
    0.98
    रों
    0.95
    lesias
    0.88
    ép
    0.87
    pt
    0.87
    trong
    0.85
    ाइवेट
    0.84
    átor
    0.82
    vět
    0.81
    痺
    0.81
    POSITIVE LOGITS
     triun
    1.34
     LOTRAchievement
    1.34
     indietro
    1.32
     home
    1.32
     veineux
    1.30
     домой
    1.27
    HOME
    1.20
     retval
    1.14
     HOME
    1.14
    home
    1.13
    Act Density 0.045%

    No Known Activations