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

    Neuronpedia

    INDEX
    Explanations

    descriptive qualifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    เปอร์
    0.42
     POW
    0.39
     डाक
    0.39
    churn
    0.38
    ConfigureAwait
    0.38
     ശക്തി
    0.38
    लिड
    0.38
     hent
    0.38
    lytres
    0.37
     convertible
    0.37
    POSITIVE LOGITS
    ំន
    0.42
    UNE
    0.37
    多种
    0.37
     unset
    0.37
     unpaid
    0.36
    EntityType
    0.36
    兩種
    0.36
     either
    0.35
    两种
    0.35
    Overall
    0.35
    Act Density 0.001%

    No Known Activations