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

    Neuronpedia

    INDEX
    Explanations

    divided into or using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contribution
    0.60
    Contribution
    0.59
    Ways
    0.54
    2
    0.54
    ann
    0.53
    dy
    0.52
    DIY
    0.52
    r
    0.50
    Item
    0.49
    Added
    0.49
    POSITIVE LOGITS
     нео
    0.58
     できる
    0.56
     極
    0.55
    を有する
    0.55
    ㄼ
    0.54
     保
    0.54
     Hartree
    0.54
     striis
    0.54
     bolstered
    0.54
     обеспечи
    0.53
    Act Density 0.000%

    No Known Activations