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

    Neuronpedia

    INDEX
    Explanations

    barrier to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mats
    0.51
    Mat
    0.48
    Mats
    0.46
     Mat
    0.45
     mat
    0.44
    mat
    0.41
     matt
    0.40
    продук
    0.40
     mattresses
    0.40
     mattress
    0.40
    POSITIVE LOGITS
     overlooking
    0.43
     rubber
    0.42
    颍
    0.41
     Fruits
    0.39
     rubbers
    0.39
    スプレイ
    0.38
    rubber
    0.38
    Rubber
    0.38
    bindung
    0.37
     guérison
    0.37
    Act Density 0.000%

    No Known Activations