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

    Neuronpedia

    INDEX
    Explanations

    nodes in neural networks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ane
    0.53
    anee
    0.47
    ately
    0.46
    product
    0.45
    ady
    0.45
    alers
    0.45
    mend
    0.43
     need
    0.42
     ย
    0.42
    aler
    0.42
    POSITIVE LOGITS
     lettera
    0.50
    uğ
    0.44
     Thrones
    0.44
     Antennes
    0.44
    ネットワーク
    0.43
    拉丁
    0.43
     Networks
    0.42
     Nodes
    0.42
     χαρακ
    0.41
     gb
    0.41
    Act Density 0.006%

    No Known Activations