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

    Neuronpedia

    INDEX
    Explanations

    set this/these/value/factor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     подготов
    1.30
    ート
    1.20
     Detta
    1.20
     sacrament
    1.15
     grained
    1.14
     uporab
    1.13
    ப்படுத்த
    1.12
     уди
    1.11
    玑
    1.09
    鰹
    1.07
    POSITIVE LOGITS
    ar
    1.46
    l
    1.28
    dır
    1.24
    der
    1.19
    ધ
    1.16
    ell
    1.13
    sm
    1.13
    bie
    1.10
    deutsche
    1.09
    γραφ
    1.07
    Act Density 0.190%

    No Known Activations