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

    Neuronpedia

    INDEX
    Explanations

    jest javascript testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    urie
    0.88
     It
    0.84
    ]
    0.83
    urul
    0.80
    ?
    0.73
    কিছু
    0.73
    dauer
    0.72
    reuses
    0.72
     Mone
    0.72
     Ched
    0.71
    POSITIVE LOGITS
    5
    1.10
    in
    1.08
    2
    1.05
    jest
    0.98
    4
    0.94
     (
    0.92
    8
    0.82
    িন
    0.82
    6
    0.81
    3
    0.79
    Act Density 0.001%

    No Known Activations