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

    Neuronpedia

    INDEX
    Explanations

    lucky numbers or draws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    scheme
    0.39
     நடத்தி
    0.39
    urpose
    0.37
     Covered
    0.37
    selValue
    0.36
     நடத்து
    0.36
    渡し
    0.36
    "]["
    0.35
     Sardinia
    0.35
    flowing
    0.35
    POSITIVE LOGITS
     le
    0.49
     luke
    0.46
     Nug
    0.46
     Creek
    0.45
     patch
    0.44
     nugget
    0.43
     Luke
    0.42
     oun
    0.42
     creek
    0.42
    DUN
    0.40
    Act Density 0.000%

    No Known Activations