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

    Neuronpedia

    INDEX
    Explanations

    unblock, unclog, unlock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    他和
    0.81
    ]
    0.70
    ]，
    0.66
     preclude
    0.66
    他
    0.63
     },{
    0.60
    ”]
    0.59
    0.59
    ”).
    0.58
     он
    0.57
    POSITIVE LOGITS
    ные
    0.84
     to
    0.81
    i
    0.80
     for
    0.77
    3
    0.77
    ام
    0.75
    યા
    0.74
     LD
    0.74
    6
    0.74
    یی
    0.72
    Act Density 0.014%

    No Known Activations