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

    Neuronpedia

    INDEX
    Explanations

    real-time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Gos
    0.41
    უთ
    0.39
     Stack
    0.39
     घटक
    0.39
     Vendors
    0.38
     घन
    0.38
    uty
    0.37
     Gos
    0.37
    vendors
    0.37
    ساب
    0.37
    POSITIVE LOGITS
     persevere
    0.47
     climbers
    0.41
    persistent
    0.38
    Omega
    0.38
    粤
    0.38
    ِن
    0.37
    Persistent
    0.36
     omega
    0.36
    INATION
    0.35
    Cutting
    0.34
    Act Density 0.002%

    No Known Activations