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

    Neuronpedia

    INDEX
    Explanations

    significantly larger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    0.94
    ні
    0.86
     torture
    0.82
    Dims
    0.77
     opinion
    0.74
    Telecom
    0.74
    Latitude
    0.74
    स
    0.74
    筧
    0.73
    Walls
    0.71
    POSITIVE LOGITS
     подойдет
    0.97
    িকালে
    0.92
    ienia
    0.91
    ihuahua
    0.90
    jekte
    0.87
     kullanarak
    0.87
    >',
    0.86
    uhnya
    0.85
    werten
    0.85
    thorace
    0.84
    Act Density 0.000%

    No Known Activations